Xiaofang Yang, Ziqi Miao, Dianbo Sui +2cs.CR cs.AI
Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions. Such skills may leak secrets, corrupt code, bypass approvals, or stage data for exfiltration only after a concrete user task and workspace state make the unsafe action appear useful. This makes pre-install vetting insufficient and calls for runtime, task-conditioned protection. We propose Defense-as-Skill, a defense paradigm that implements the runtime guard itself as an installable, inspectable, and editable skill. Our guard, SkillSonar, runs alongside untrusted task skills and checks sensitive actions against the user's task boundary, routing each action to an allow, replan, or confirmation decision without modifying the underlying agent runtime. To study this setting, we construct SCOPE-R, a task-conditioned dataset covering 6 risk families and 21 sub-categories, with 206 attack-confirmed malicious instances and 43 benign tasks. We then improve SkillSonar on the SCOPE-R training subset using runtime guard-skill evolution, a Monte-Carlo Tree Search procedure that evolves the on-disk guard skill from feedback on the rollouts. Across Claude Code and OpenClaw, the evolved guard substantially reduces attack success while maintaining a favorable safety-utility trade-off. On repeated GLM-5 runs, SkillSonar reduces ID ASR from 0.482 to 0.104 and OOD ASR from 0.606 to 0.115. Further analyses demonstrate transfer across victim models, held-out risk families, and external benchmarks, as well as retained protection against adaptive attackers. Ablations further show that explicit safety responsibility assignment and the skill-native representation are both important to the observed gains.
AI agents are moving toward persistent, stateful execution across various applications, accumulating execution state and external effects that are costly to reconstruct after failures. Checkpoint and rollback (C/R) are becoming essential for recovery, yet their security implications remain largely unexplored. Correct rollback does not imply secure recovery: a faithfully restored checkpoint may resume an execution whose states, assumptions, and external effects never coexisted in any valid history. In this paper, we present the first systematic security study of checkpoint and rollback in existing agent systems. By examining representative agent C/R systems, we characterize the design space of existing C/R mechanisms and develop a general execution model that captures their recovery boundaries and state dependencies. From this model, we identify five fundamental failure modes spanning incomplete or inconsistent internal state, stale external dependencies, nondeterministic replay, and unrecorded external effects. We further demonstrate their security impact through three end-to-end attacks on Hermes, Cline, and LangGraph, enabling malware-verification bypass, unauthorized mail forwarding, and double payment. To systematically study these failures in practice, we develop a multi-agent analysis pipeline that reconstructs execution semantics, identifies violations of the five failure conditions, and validates them through actual rollback. Across five representative frameworks, our evaluation shows that these failures recur across heterogeneous C/R designs and stem from a common gap between the state restored by a checkpoint and the dependencies required for secure continuation.
Agent skills bundle instructions, reference data, and executable helpers that let a general agent perform specialized tasks. Hosted providers can keep these files secret while selling access to task results, making the skill itself a valuable target. Existing disclosure defenses can block requests that ask for the skill or reproduce its text, but they cannot block customers from submitting the ordinary tasks the service is built to complete. We present Daydreaming, an execution-only attack that steals a multi-file skill through black-box task interactions. The victim is never asked to reveal the skill or grade a reconstruction. Instead, Daydreaming adaptively creates crafted tasks whose results distinguish possible hidden behaviors. It tests individual behaviors, uses attacker-controlled shadow agents to choose a design, and completes each file using stored victim results and local execution checks. We formalize three nested threat levels of access as Differential, Trace, and Output, and focus on Output, where the attacker sees only the final response and returned files. Across 7 skills and 4 victim models, Daydreaming recovers 86.8% of the original skill's capability at Output, outperforming SigLeak by almost 4x. It produces installable skills using a median of 32 victim calls per skill even with disclosure defenses enabled. These results show that hiding skill files and filtering direct disclosure do not, by themselves, prevent functional reconstruction through normal use.
Self-evolving Skill harnesses (AutoSkills, Hermes Agent) generate more advisory orchestration automatically; their reported gains are efficiency, not safety. This misses the actual gap: a Skill describes how an agent should behave; a Policy decides which behavior is allowed to become an action. Today's format covers the first with markdown and scripts; the second is left to the model. Generating more Skills scales the gap, not the safety, especially when a wrong invocation can unlock a door or move money. Two adjacent attacks are documented: malicious skills compromising cloud software, and jailbroken LLM-controlled robots causing physical harm. Their intersection, malicious agent skills causing physical harm, follows directly but has not been reported. We name this class Borrowed Authority: Skills format gives the receiving agent no typed way to reject an inter-agent permission claim, so a malicious or misused Skill can drive actuation by attaching one. We propose Edge Skillguard, a typed authority layer that lives inside the Skill artifact rather than between tools as workflow engines do, with guards over world state and sensor evidence. On a live edge control-plane testbed, the guards reject 60/60 borrowed-authority requests across five attack variants without blocking benign requests, and the result holds at 5x scale and across hosts over a Tailscale mesh. These results suggest that high-risk Skills should co-package typed invocation policy with procedural knowledge, so that physical actions depend on machine-checkable evidence rather than peer-agent claims.
Minjae Seo, Wonwoo Choi, Geonwoo Han +7cs.AI cs.CY
Personal AI agents routinely consume external content while performing tasks such as web browsing, email processing, and SNS feed summarization, and they retain selected information or execution results in persistent memory for later use. We show that this ordinary ingestion of external content opens an indirect path for manipulating subsequent agent behavior. Based on this observation, we present IBIA, an Indirect Bias Injection Attack that plants an adversary-aligned stance on a specific topic into a victim agent's memory through external content, without direct access to the agent, its memory, or future user queries. For this, IBIA combines three mechanisms: comment cloaking, which keeps the crafted content consistent with the surrounding discussion, comment watermarking, which enables lightweight identification during curation, and category anchoring, which makes the retained stance salient under later related requests. We evaluate IBIA on BiasBench, a benchmark of 6,000 adversary-crafted social comments and 120 email instances. The watermark-based curation identifies 95.9% of the injected comments. Under the OpenClaw setting, IBIA achieves adversary-aligned response rates (AARs) of 91.2% on average across four downstream tasks, including 86.6% on the frontier GPT-5.5. We further propose a memory boundary defense that detects the injected bias and reduces AARs to 80.6%.
Persistent memory makes false information durable: once a false statement is stored, it can be retrieved into future sessions that match it. We measure the cost of this failure mode using plainly worded false assertions generated in a single pass, with no instruction, trigger, or retriever optimization. Poisoning 1.2% of a LongMemEval corpus reduces accuracy from 0.850 to 0.300. A four-stage write-time screening pipeline that reaches 0.832 recall on indirect prompt injection while flagging 1.5% of trigger-word-laden benign text rejects 0 of 360 poisoned memories. We argue this exposes a boundary of content-only screening: distinguishing a false assertion from a true one generally requires external grounding beyond the text itself. We then evaluate provenance-weighted retrieval. The shipped weight is statistically indistinguishable from no defense (p=0.80), while a stronger weight recovers utility only by excluding untrusted content. In a mixed-provenance corpus where untrusted content is mostly benign, accuracy rises from 0.3167 to 0.7000; when the answer-bearing evidence itself arrives untrusted, evidence recall falls to zero and accuracy to 0.0417. Under the measured similarity regime, the additive provenance term has no usable setting: a weight strong enough to resist query-shaped poison is also strong enough to suppress legitimate untrusted evidence. We therefore argue for bounded occupancy constraints at retrieval rather than additive provenance penalties, and release the harnesses, corpora, and aggregate run reports.
Rabimba Karanjai, Yang Lu, Nour Diallo +4cs.CR cs.AI
AI agents increasingly act rather than merely read: across the Model Context Protocol (MCP) ecosystem, the share of deployed tools that modify external state has risen from 27% to 65% of tool use. When agents exercise this authority on public blockchains through MCP, skills, and tool calling, the consequences of an attack are governed by the blockchain execution layer rather than by conventional software assumptions. This survey argues that four properties of that layer (irreversibility, signing authority, continuous autonomy, and sequence-level composition) qualitatively change the threat model, turning the recoverable failures of generic agent security into a standing, irreversible loss. We organize the fragmented MCP-security literature into an attack-surface taxonomy, then contribute a Web3 risk-mapping matrix that ties each attack class to its amplified impact, the responsible amplifiers, a representative mitigation, and the residual gap. We synthesize defenses, including emerging blockchain-based mechanisms, and find them improving but insufficient: measured protections stop fewer than 30% of attacks, and model-level safety refuses fewer than 3%. We close by positioning the work against adjacent surveys and deriving a research agenda from the matrix's open cells.
Large language model agents are increasingly connected to high-value resources such as computing infrastructure, credentials, usage budgets, identities, private knowledge, communication channels, and organizational workflows. Existing agent security research mainly studies attacks on instructions, data, and tool behaviors, while high-value resources accessible to agents have received much less attention as direct attack targets. We are the first to identify and systematically study agent resource hijacking, a security blind spot in which attackers induce agents to invoke, consume, transfer, or control high-value resources for their own goals without directly obtaining those resources or their credentials. To study this threat, we introduce ResourceHijackBench together with an automated pipeline for generating resource hijacking cases. We organize high-value agent resources into six categories and construct 300 attack scenarios with 900 attack prompts. Each case runs in an isolated local environment that records actual resource use, allowing attacks to be evaluated from agent behavior rather than text responses alone. Without additional defenses, OpenClaw reaches an average attack success rate of 84.06%. The attack remains effective across different model backends, with average success rates ranging from 69.98% to 89.58%. Existing defenses reduce part of the risk, but the strongest evaluated defense still leaves an average attack success rate of 55.11%. These results show that high-value resources accessible to agents form an important and previously overlooked attack surface, and that current agent defenses are not sufficient to protect them from resource hijacking.
Sanjay Kariyappa, Severin Klingler, G. Edward Suhcs.CR cs.AI
Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or what it should convey. We show that this gap enables state-corruption attacks, in which attacker-controlled content makes environmental claims beyond the informational authority of its response component and corrupts the agent's perceived environment, making the resulting action appear justified to existing guardrails. We introduce PIPES (Provenance-Informed, Prior-Enforced Screening), which screens response units using semantic priors and source provenance. PIPES uses static field contracts when schemas provide stable expectations, and conditions screening of open-ended content on the pre-response trajectory and trusted provenance metadata. It marks units that violate their semantic prior or the provenance hierarchy; deployments may remove, warn, block, or escalate detected violations. We instantiate atomic removal and evaluate PIPES against adaptive PAIR-style attacks. Across the three VitaBench and three AgentDyn splits with Gemma 4 31B IT as the target agent, PIPES reduces average attack success from 84.7% to 2.3%, while preserving average benign utility (92.5% with PIPES versus 90.6% without defense).
Md Jafrin Hossain, Mohammad Arif Hossain, Nirwan Ansarics.CR cs.AI
Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory. When these agents operate with real-world privileges---calling APIs, modifying files, and querying databases---a compromised reasoning step can trigger unauthorized data access, irreversible state changes, or cascading failures, yet the security research community has not kept pace. To quantify the state of the field, we conducted a systematic literature review under PRISMA 2020 guidelines across six databases, screening 743 records and retaining 85 papers (2023--2025) on agentic LLM security. Attack research outpaces defense work by 3.9:1. Perception-layer vulnerabilities (prompt injection, jailbreaking, adversarial perturbations) dominate, accounting for 66\% of papers, while action-layer vulnerabilities (tool misuse, code injection, sandbox escape) appear in only 4.7\%, misaligned with real-world risk. Code execution security accounts for 3.5\%, and tool-augmented agents 12\%. We contribute a four-layer taxonomy mapping 13 vulnerability types across perception, brain, action, and interaction layers, and identify seven open problems centered on containment. Agentic LLM insecurity stems from architectural coupling, where weak isolation allows vulnerabilities to propagate across layers.
Agent skills are emerging as an important attack surface in LLM-based agent systems. Through an empirical study of existing skill scanners, we find that current defenses mainly inspect individual skills, leaving risks from cross-skill composition insufficiently examined. This creates a practical blind spot: multiple locally plausible skills may pass security checks while collectively forming a harmful workflow during agent execution. To investigate this threat, we propose ColluSkill, a collusive multi-skill-chain attack framework that decomposes a complete malicious intent into interdependent sub-payloads embedded in independently packaged skills. The attack does not rely on any single malicious skill, but emerges from the ordered composition of locally plausible behaviors through contextual dependencies, artifact passing, and execution handoffs. ColluSkill further employs LLM-based chain planning and scanner-feedback refinement to preserve chain-level attack semantics while reducing suspicious signals in individual sub-skills. To defend against such attacks, we propose ChainGuard, a context-aware skill-chain scanner that jointly analyzes a candidate skill and the skills already installed in the agent environment. ChainGuard reconstructs cross-skill dependencies, artifact flows, capability compositions, and downstream behaviors to identify risks that emerge only at the workflow level. Experiments on six representative skill scanners show that ColluSkill achieves an average attack success rate of 96.0% and consistently outperforms the evaluated single-skill and multi-skill attack baselines. Meanwhile, ChainGuard reduces the attack success rate to 22.5% while allowing 99.5% of benign workflows to pass, highlighting the importance of chain-level security analysis for agent skill ecosystems.
Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security properties remain under-explored. We present \textsc{SkillsMetric}, a five-stage static analysis framework that scores skill packages along pattern density, statistical anomaly, dataflow taint, import anomaly, and capability mismatch dimensions. We construct an adversarial evaluation dataset of 2{,}266 skills spanning 16~attack types across code-level, system-level, and semantic-level threats, and evaluate on the full SkillMD-138K corpus. Our framework achieves an AUC of 0.93 and 5-fold cross-validated F1 of 73.4\%$\pm$0.5\%, with strong detection of data exfiltration (93\%) and steganographic payloads (93\%). Crucially, we identify fundamental blind spots: \emph{host destruction} attacks using common shell commands evade all five stages (0\% detection), and \emph{prompt injection} via natural-language manipulation achieves only 42\% detection. These findings establish that static analysis alone is insufficient for skill security, motivating defense-in-depth architectures that combine fast static pre-screening with semantic review.
AI agents performing cryptographic operations (signing Git commits, authenticating API calls, issuing certificates) currently store private keys in software-accessible locations: plaintext files, environment variables, or container memory. Any process with sufficient read privileges can extract the raw key material. A recent production incident demonstrated the practical severity: private keys were exfiltrated from a widely deployed framework via email injection in under five minutes. We aim to enforce both key confidentiality and content-aware authorisation for key use. To that end, we replace software-resident keys with hardware-confined keys accessible through a vendor-neutral PKCS#11 interface. A hardware keystore (HSM, TPM, smart card) executes cryptographic operations on-device; the host receives only the result via opaque handles. Hardware confinement is the primary contribution; it is enabled by a surrounding five-layer Zero-Trust enforcement stack comprising session identity (SAGA), scope bounds (Smax), semantic validation (RAV), taint tracking, and the hardware execution boundary. We evaluate against 12 injection scenarios derived from AgentDojo's ImportantInstructionsAttack template (Debenedetti et al., arXiv:2406.13352). We run four LLM models; three follow injections in baseline mode (gpt-oss-120b, Qwen2.5-72B, DeepSeek-V4-Flash, n=192 combined). Baseline Attack Success Rate (ASR): 19.3% [14.3%, 25.4%]; protected ASR: 0% (Wilson 95% CI upper bound 2.0%). Zero false positives across four benign task scenarios.
Prince Zizhuang Wang, Aojie Yuan, Haiyue Zhang +3cs.AI
Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these networks, everyday tool use becomes multi-party owned-agent collaboration over personal workspaces, where files, records, tools, and policies are not directly visible across owners. Existing agent benchmarks study tool use and collaboration, but they do not provide an end-to-end sandbox for verifiable cross-user agent collaboration with realistic user digital workspaces or test how harmful actions can travel through the human-centered agent network. We introduce WeClawArena, an auditable benchmark and runtime sandbox for multi-party owned-agent collaboration over personal workspaces. WeClawArena targets collaborative tool-use tasks in which personal workspaces serve as both operational tools and personal constraints. The benchmark contains 124 base tasks across six cross-user task domains and expands them into 620 scenario variants, with one benign control and four attack-vector variants per base task. The sandbox records peer messages, tool calls, resource operations, governed decisions, and final workspace states. WeClawArena reports utility and attack success rate separately and audits attack success from bounded runtime evidence, supporting diagnosis of task breakdown, privacy leakage, poisoned evidence, and invalid authority paths.
Tool-using agents built on large language models (LLMs) are increasingly deployed not by a single operator but by many, side by side on shared infrastructure. This creates a population-level risk that single-agent safeguards miss: a handful of agents can quietly coordinate, rigging a market, boosting one another in a review process, or timing a joint data grab, while each one looks perfectly well-behaved. The difficulty is that the organisations running these agents cannot see inside one another's models, so any realistic detector must work from behaviour alone: black-box, trace-only, and often with only partial visibility. We treat covert coordination as an information-hiding problem and build a black-box steganalysis detector that combines cross-run mutual-information estimation, permutation tests, distributional-shift statistics, and timing and tool-call side channels, all calibrated to a fixed false-positive budget. Our central move is to stop testing against a single fixed code: we pit the detector against an adversary that continually rewrites its encoding to slip past whatever the detector has learned, and we run this red-versus-blue contest in tool-using, memory-carrying environments rather than toy games. Capacity theory then tells us what to expect, a detection-capacity frontier, a covert bit-rate below which black-box detection is provably no better than chance. We set out an experiment to map this frontier, report clearly labelled placeholder results pending measurement, and flag a practical evasion, spreading a payload across sessions, that current methods largely miss.
Autonomous agents are increasingly used to execute consequential tasks in environments governed by operational constraints, organizational policies, regulatory requirements, and technical standards. Their safety is therefore determined not by the correctness of individual actions, but by whether their overall behavior remains consistent with the rules and invariants of the systems in which they operate. As large language model (LLM)-based agents become more autonomous and increasingly delegate tasks across organizational boundaries, securing them evolves from a single challenge into a broad and interconnected landscape spanning the entire agentic stack. At the single-agent level, untrusted inputs through prompts, memory, retrieved knowledge, and tool interfaces create attack surfaces. In multi-agent settings, delegation and communication introduce challenges related to identity, trust, capability control, and decision transparency, while the underlying model routing and execution control plane remains vulnerable to manipulation and to unverified model provenance. Perhaps the most fundamental challenge is behavioral containment: sequences of individually permissible actions may collectively violate system-level constraints and safety invariants. At the broader level, supply-chain integrity, provenance, accountability, and end-to-end observability remain largely open problems. A common principle unifies these directions: security must become a verifiable property of the architectures, protocols, and runtimes that govern agent behavior, rather than an optional layer of guidance. Charting these challenges provides a roadmap toward trustworthy autonomous agent deployment.
Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker may be stored in long-term memory, recalled much later, and quietly shape a real action. Recent benchmarks increasingly examine agent memory security, yet few trace the same malicious semantics across persistence, downstream consequences, and selective repair under diverse memory-backend comparisons. To address this gap, we introduce MemSecBench, a task-grounded benchmark for the lifecycle security of agent memory systems. It contains 310 cases drawn from 48 realistic contexts across code and science, daily life, and office work. Each case follows a controlled Write--Execute--Forget protocol in an isolated runtime under an exact agent configuration, defined by an agent harness, a memory backend, and an LLM backend. Evidence-based adjudication combines a deterministic write check, checkpoint-specific judge-model evaluations, and programmatic gates across seven lifecycle checkpoints. The experimental design spans a 24-configuration matrix of two agent harnesses, four memory backends, and three LLM backends. Across all 24 configurations, malicious memory persists in 84.2% of all cases, and the full Write--Execute chain succeeds in 50.3%. Among successfully poisoned cases, 59.6% complete the full Execute chain, while 56.1% achieve selective repair.Compared with matched Native configurations, the largest absolute differences are 16.1 percentage points for end-to-end attack success and 41.3 percentage points for selective repair. These descriptive contrasts indicate that the evaluated memory system stacks differ in lifecycle security, both in the propagation of malicious memory and in selective repair after successful memory poisoning.
AI coding agents are being adopted at historic speed, yet security and risk concerns remain the primary barrier to scaling agentic AI across organizations. Existing security controls for coding agents are not systematically distributed to engineering teams, and vendor-native solutions introduce ecosystem dependencies that may not suit every deployment context. This paper investigates whether off-the-shelf security controls can be implemented on commercial AI coding agents and scaled to a distributed user base via a custom agent harness. A phased testing methodology was applied across four agent configurations --- two commercial agents with and without controls, a baseline harness, and a security-hardened harness --- using a 23-test suite derived from the OWASP Top 10 for Agentic Applications. SHarD (Secure Harness Distribution), a distributable harness built on the Pi agent harness, demonstrated that three categories of security controls --- OS sandboxing, skill scanning, and tool restriction --- can be embedded and distributed via a single install command while retaining equivalent efficacy to direct installation on commercial agents. SHarD achieved an adjusted score of 100\%, matching the best securely configured commercial agent, with no regression across any test category. Notable observations include evidence that model non-determinism produces inconsistent security outcomes and that autonomous agent behavior can cross system boundaries in ways that OS sandboxing directly mitigates. Initial characteristics toward a control harness fitness framework are proposed, and a third research question is identified for future investigation.
Erik Imgrund, Anna Wimbauer, Klim Kireev +1cs.CR cs.AI
Large language models now power autonomous agents capable of complex, multi-step tasks in different environments. Accurate and reliable execution of these tasks requires the agent to predict the results of its actions. Recent research proposes to enhance predictive capabilities via specially trained environment simulators-world models. While world models can improve performance, they can also mislead agents into executing harmful actions, creating significant security and privacy risks. In this paper, we raise security concerns regarding the usage of world models in agentic systems. We discover a range of world model specific vulnerabilities, which can be exploited in terminal-based agents to execute malicious code or extract sensitive data. To facilitate future development, we introduce a security benchmark dataset designed for text-based world models. We argue that some risks are intrinsic to approximate world modeling, and show that attackers can induce mispredictions in agentic pipelines with up to 95% success rate, possibly resulting in unintended command execution, denial of service, drainage of wallet and private information extraction. Finally, we provide practical recommendations for practitioners to mitigate the discovered harms and harden agentic systems.
Vincent Siu, Jingxuan He, Kyle Montgomery +3cs.CR cs.AI
Agent security is widely treated as a question about action content. Defenses ask whether an instruction looks malicious. Benchmarks ask whether an agent performs a harmful sounding action. \textbf{We argue that agent security is fundamentally a contextual problem, and that the current content based framing systematically misdefines it.} A command to ``delete user data'' might be a routine administrative request or a prompt injection attacking production systems, and the content alone cannot distinguish the two. Authorization context can. Across every injection task in AgentDojo and WASP, the same action is one an authenticated user would plausibly request in a routine workflow, which makes the conflation a structural property of evaluating security through content. We operationalize contextual security through four properties that must hold jointly and be evaluated continuously across the agent's trajectory. Source Authorization asks who issued the command. Task Alignment specifies the agent's authorized objective. Action Alignment evaluates whether each action serves that objective. Data Isolation governs information flows across privilege boundaries. Under this reframing, indirect prompt injection becomes a Source Authorization violation. Snapshot benchmarks are structurally incapable of evaluating Data Isolation. Existing defenses are reorganized around the property they actually approximate. The contextual reframing changes which defenses are coherent, which evaluations measure something useful, and which attack patterns evaluation can see at all.
LLM agents increasingly rely on external tools, expanding capability while creating a new security boundary: third-party tools may appear benign at the interface level while embedding unsafe behavior in implementation. Existing defenses rely on weak metadata, collapse characterization and policy judgment into a single decision, or use heuristic/LLM enforcement that lacks deterministic, auditable reasoning over task context and multi-tool composition. This paper presents ToolGuardian, a policy-driven framework for securing agent-tool interactions through pre-admission vetting and task-aware runtime authorization. ToolGuardian uses progressive characterization to convert evidence into structured facts: descriptions capture declared intent, system-call traces expose coarse behavior, mock execution reveals observed effects, and source analysis identifies latent behavior. ToolGuardian's core contribution is an Answer Set Programming (ASP)-based declarative policy layer that reasons explicitly over capabilities, effects, task context, and composition. We compare ASP against heuristic and LLM-based policy realizations using identical inputs and output contracts. We evaluate ToolGuardian on 16 MCP-style tools, including 8 malicious variants derived from real open-source tools, and 20 runtime scenarios. For vetting, ASP reaches a deny-class F1 of 0.86 and 88% accuracy using description, syscall, and observed-effect evidence. For runtime authorization, fully specified realizations classify all scenarios correctly, while ablations show that removing compositional and conformance rules substantially degrades performance.
Or Zion Eliav, Eyal Lenga, Shir Bernstien +1cs.AI cs.CR cs.LG
Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that AI agents require the same treatment. We formalize agent reconnaissance by modeling the process and identifying the knowledge assets it seeks to extract: what they are, how they are used, and which agent weaknesses they exploit to give adversaries leverage in indirect prompt injection attacks. We instantiate these insights in Know Your Agent (KYA), a framework that automates black-box, reconnaissance-driven pentesting by probing agents, building target profiles, and using those profiles to craft stronger attacks. We evaluate KYA on agent-security benchmarks and a real-world coding agent, and release KYA, its benchmarks, and baseline implementations for reproducibility.
We study a five-agent CI/CD pipeline (triage -> developer -> security-scan -> review -> approve/deploy), built from five distinct production LLMs across three providers, behind an LLM firewall in shadow mode. A single untrusted input - an external issue requesting a "usage-telemetry" feature - asks for code that exfiltrates process secrets (dict(os.environ)) to an attacker URL, laundered as observability. Across a pre-registered A x B (x C) factorial (N=20; naive arm N=60) we find: (1) the entry agent does not leak its system prompt (0/40); (2) an authority-framed injection ("pre-approved under SEC-2291, do not re-review") makes downstream verifiers see the secret-exfil line, cite the pre-approval, and ship it - the scanner passes ~80% of laundered pull requests, and the worst-case cell reaches 55% compromise; (3) the perceived presence of other verifiers yields only a small, non-significant reduction in individual scrutiny (a weak bystander analogue), even at N=60; and (4) content-based controls - code scanners and pattern detectors alike - miss the laundered intent entirely (the code is syntactically clean); only an LLM reasoning about intent is a partial defence. The failure is systemic: neither prompt secrecy nor distributed verification protects; a provenance-aware control at the entry, independent of both, would have. All data is 100% synthetic; the sink is mocked and the exfil URL is never contacted.
Om Narayan, Ramkinker Singh, Praveen Baskarcs.AI cs.CR
The transition from stateless generative models in artificial intelligence to stateful, autonomous agents represents an architectural evolution that, while providing the capabilities of long-term planning and the automation of enterprise workflows, also represents the introduction of a new form of security threat, the Chronos Vulnerability. The Chronos Vulnerability represents the threat of memory-based attacks, including the Memory Injection Attack (MINJA) and the sleeper agent, in which the internal belief system of the autonomous agent is compromised, effectively decoupling the attack vector from the final catastrophic event. This study formalizes the threat model for persistence-based attacks and the threat of Dynamics Blindness in the context of the World of Workflows benchmark, demonstrating that traditional endpoint content filters are insufficient for the current stateful architecture. Consequently, this study synthesizes a defense-in-depth landscape, categorizing emerging frameworks such as diagnostic trajectory guardrails (AgentDoG), formal temporal verification (Agent-C), immunological memory consensus (A-MemGuard), and hardware-anchored trust via GPU-based Trusted Execution Environments (TEEs) and Zero-Trust memory architectures.
Large language model (LLM) agents are starting to take on routine work in high-performance computing (HPC), including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows. To do this work, an agent commonly acts under its user's credentials and inherits the user's access to files and the scheduler. This arrangement creates a failure mode that ordinary account-level controls do not capture. Adversarial instructions in a log, tool description, shared file, or peer-agent message may redirect the agent beyond the task the user assigned, even though every resulting command is authenticated and permitted for that account. We refer to this as the hijacked authorized agent problem. Existing agent-security studies explain relevant mechanisms, such as indirect prompt injection and tool misuse, but generally evaluate them in web, enterprise, or personal-assistant settings. HPC security, by contrast, has mature controls for identity and isolation but does not ordinarily represent the intent of a particular task. This paper defines the threat model in the HPC setting, identifies attack surfaces created by schedulers, shared storage, multi-project accounts, and scientific workflows, and examines where current controls fall short. It concludes with a research agenda and a plan for an empirical benchmark, TaskBound.
Devina Jain, David Hartmann, Chuan Lics.CR cs.AI cs.LG
LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation. Most safety benchmarks evaluate defenders against fixed attack pools collected before evaluation, single-turn or multi-turn. We present a 21-scenario benchmark for \emph{adaptive multi-round attacks against memoryless LLM defenders}: an autonomous LLM attacker observes prior defender responses and pivots across rounds, while each defender response is evaluated as a fresh interaction. Holding the 21 scenarios, attackers, defenders, and structured-output scoring fixed, restricting scoring to the first attacker turn yields $0$-$1\%$ attack success rate (ASR); allowing 15 rounds of adaptive attack yields $5.4$-$14.0\%$. Pooling three frontier attacker LLMs uncovers $1.4$-$2.2\times$ as many unique successful attacks as the best single attacker, and the generated attacks have low cosine similarity ($0.02$-$0.14$) to attacks in existing benchmarks. Claude Opus 4.6 and GPT-5.4 are tied in aggregate ($5.4\%$ each; overlapping $95\%$ CIs), but their weaknesses differ sharply: on one scenario Opus reaches $60\%$ ASR ($95\%$ CI $36$--$80\%$) while GPT-5.4 and Gemini each stay at $7\%$ (CI $1$-$30\%$; the gap is preserved in a higher-$N$ replication). $13$ of $21$ scenarios distinguish at least one defender pair, yet rankings disagree across scenarios (Kendall's $W = 0.19$). We release the benchmark -- 21 evaluation scenarios, 10 public development scenarios, the orchestrator, baseline harnesses, and a multi-attacker CLI -- plus 945 transcripts from the 3$\times$3 frontier matrix, an attack-replay dataset, and 18{,}422 gpt-oss-20b battles from an open competition's final scoring rounds.
Soham Gadgil, David Alexander, Sai Sunku +1cs.CR cs.AI cs.MA
A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases. While this makes agents more useful and self-improving, it also creates a new attack surface for prompt injections in which malicious instructions can be embedded within persistent files and influence future behavior. In this work, we study prompt injection attacks in memory-based agentic systems using a sandboxed synthetic workspace. We evaluate two agentic systems, Anthropic Claude Code and OpenAI Codex, across four models: Claude Haiku 4.5, Claude Opus 4.7, GPT-5.2, and GPT-5.5. Our results show that although it is difficult to make an agent overwrite its own memory files using untrusted external content, payloads already planted in those files can successfully attack current and future sessions. Attack success and payload persistence vary substantially across systems, models, adversarial goals, and multi-session attack sequences. These findings show that persistent memory changes the threat model for prompt injection and motivate defenses that protect memory updates without removing useful agent adaptation.
Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not. We argue that this binary attack-success rate discards the information a defender most needs, namely how harmful the resulting action was. We introduce an action-graded harm rubric that scores an agent's tool-call trajectory on a seven-level ordinal scale (L0 to L6) according to whether the executed action was reversible, whether it crossed scope to reach another party, and whether it expanded privilege. We compute the scale two ways: a deterministic oracle that reads the trajectory and the attacker's stated goal, and a panel of three frontier language-model judges that read a tag-free account of the same trajectory. Across four victim models and two defenses on the AgentDojo workspace suite, severity grading exposes three cases the binary metric hides, including a defense that reports a zero attack-success rate while still permitting an externally visible cross-scope leak through an unfiltered tool. The judge panel reproduces the oracle with high ordinal agreement (Krippendorff's alpha = 0.91) but shares systematic blind spots that we characterize, most notably a failure to recognize escalation chains. Unlike prior work that provides harm taxonomies, harmful-task completion tests, execution-level safety benchmarks, or severity-aware simulation, our contribution is a reusable, trace-grounded severity instrument applied to the actual actions recorded in existing red-team logs. All code, prompts, and per-episode logs are released.
Woohyuk Choi, Juhee Kim, Taehyun Kang +3cs.CR cs.AI
AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security has primarily focused on indirect prompt injection (IPI). Its most well-studied category is instruction injection, where attacker-controlled untrusted data is interpreted as an instruction. In response, many mitigations have been proposed to prevent instruction injection attacks. In this paper, we introduce a new category of IPI, agent data injection attacks (ADI). ADI injects malicious data disguised as trusted data, such as security-critical metadata (e.g., resource identifiers or data origins) or agent context data (e.g., tool call and response formats). As a result, agents unknowingly execute unintended actions based on attacker-controlled data. ADI has similar attack impacts as instruction injection attacks, because it causes agents to misbehave and execute unintended actions. Despite the similar impact, ADI remains underexplored and easily bypasses existing IPI defenses. We found several critical vulnerabilities in real-world agents that allow an attacker to launch various attacks: arbitrary click attacks on web agents (Claude in Chrome, Antigravity, and Nanobrowser), and remote code execution and supply-chain attacks on coding agents (Claude Code, Codex, and Gemini CLI). We evaluate ADI vulnerabilities across off-the-shelf models and AI agents, and find that ADI is effective in both standalone LLMs and AI agent settings. ADI exposes a critical gap in agent security, signifying that current AI agents do not employ a fundamental security principle: current agents do not isolate trusted data from untrusted data.
Chris Schneider, Kriti Faujdar, Philipp Schoenegger +1cs.CR cs.AI
Modern AI agent implementations such as frontier coding agents chain multiple tools at runtime that create a security surface that per-tool guardrails are unable to address, as individually permitted tools can violate organizational policies when composed. We propose the Dynamic Security Control Compositor (DSCC), a two-phase approach to compositional security for multi-tool agent chains. In Phase 1, at session checkout, a Most Restrictive Set (MRS) algorithm composes per-tool security policies into a single effective policy with a formal monotonicity invariant that extending a chain can only tighten the result, blocking incompatible combinations before any tool executes. Outputs of any tool call propagate their classification constraints into a session-level taint state, so subsequent invocations must satisfy the most restrictive constraints seen so far. In Phase 2, at runtime, the system tracks the sensitivity of data the agent touches through a monotonic taint state and revokes the session if the accumulated exposure would make a subsequent tool call a policy violation. Together, these phases provide defense in depth, where static composition prevents unsafe chains from starting, and runtime taint tracking catches violations that emerge from the specific data used. We provide a reference implementation on 32 tools governed by 16 NIST SP 800-53 aligned policies and evaluate it under two composition modes. In the default clearance mode, permitted combinations are partitioned into classification-level clusters, blocking 79.2% of policy pairs and 95.5% of triples. The alternative taint mode admits mixed-classification chains within the exfiltration boundary, blocking 42.5% and 60.5% respectively. We discuss the governance implications for organizations deploying multi-tool agents, including the utility-security tradeoff and the changes needed to operationalize chain-aware policies.