The paper introduces SkillSafetyBench, a comprehensive benchmark demonstrating that agent safety failures often stem from adversarial influences within reusable skills and execution environments, rath…

The paper introduces MalSkills, a neuro-symbolic framework that detects malicious skills in the expanding agentic supply chain by analyzing security-sensitive operations across heterogeneous artifacts…

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, unad…

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, expl…

This paper presents the first systematic study of black-box skill stealing attacks against proprietary LLM agents, demonstrating that structured agent skills can be easily extracted, posing a signific…

The paper introduces LoopTrap, an automated red-teaming framework that demonstrates how malicious prompts can poison the termination judgment of LLM agents, causing unbounded computation.

The paper introduces Document-Driven Implicit Payload Execution (DDIPE) to demonstrate that malicious code can be embedded in LLM agent skill documentation, allowing supply-chain attacks to hijack age…

RouteGuard is a novel detector that identifies skill poisoning in LLM agents by monitoring structured internal attention shifts, achieving high detection rates on critical skill-injection attacks.

The paper introduces SkillHarm, a comprehensive benchmark and automated framework for evaluating skill-based attacks across the entire agent skill-use lifecycle, demonstrating that current agents rema…

The paper proposes agentic fuzzing, a novel bug-finding approach where deep agents perform direct reasoning based on historical bugs to discover logic bugs in mature codebases.

The paper introduces BadSkill, a novel backdoor attack formulation that targets third-party agent skills by poisoning the embedded model artifacts, achieving high attack success rates across various m…

ClawGuard is a novel runtime security framework that deterministically enforces user-confirmed rules at tool-call boundaries to protect LLM agents from indirect prompt injection.

The paper systematically maps LLM agent vulnerabilities by testing 10,000 prompt variations, finding that 'goal reframing' language is the primary trigger for exploitation, rather than broad adversari…

This study conducts a large-scale empirical analysis of third-party LLM agent skills, identifying that credential leakage is a pervasive, cross-modal issue primarily caused by debug logging and result…

The paper introduces AgentTrap, a dynamic benchmark that measures LLM agent susceptibility to malicious side effects embedded within seemingly benign third-party skills, finding that agents often exec…

The paper introduces AgentSecBench, a security evaluation framework that measures prompt injection, privacy leakage, and tool-use integrity in LLM agents by defining formal security games and testing…

SkillAttack is a red-teaming framework that dynamically tests the exploitability of latent vulnerabilities in LLM agent skills using adversarial prompting, demonstrating that even benign skills pose s…

The paper proposes a trust schema and verification framework to ensure that agent skills, which augment LLMs, are rigorously verified before deployment, thereby making human-in-the-loop oversight scal…

The paper introduces Behavioral Integrity Verification (BIV), a framework that systematically audits AI agent skills by comparing their declared capabilities against their actual implementation, revea…

SkillTrojan introduces a novel backdoor attack targeting the composition of reusable skills in agent systems, demonstrating high attack success rates with minimal impact on normal system functionality…