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

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…

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 introduces SkillVetBench, a novel two-stage benchmark that effectively detects and verifies malicious behavior in open agentic skill ecosystems, significantly outperforming existing static a…

The paper introduces SkillVetBench, a novel two-stage benchmark that effectively detects and verifies malicious behavior hidden within open agentic skills, significantly outperforming static and seman…

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…

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…

The paper proposes SkillProbe, a multi-agent security auditing framework, demonstrating that high-popularity skills in LLM agent marketplaces are often insecure due to systemic combinatorial risks.

The paper introduces Proteus, a self-evolving red-team framework that measures the adaptive leakage risk of LLM agent skills, demonstrating that current vetting methods significantly underestimate res…

This paper conducts a large-scale, repository-aware security analysis of AI agent skills, demonstrating that incorporating surrounding project context drastically reduces the rate of false positive ma…

This paper provides the first comprehensive security analysis of the Agent Skills framework, identifying severe structural vulnerabilities that require fundamental architectural changes rather than si…

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…

SkillSieve introduces a three-layer hierarchical framework to detect malicious AI agent skills, achieving high F1 scores (0.920) on a large-scale benchmark while maintaining low operational costs.

This paper demonstrates that the natural language metadata (SKILL.md) used to describe AI agent skills introduces significant semantic supply-chain risks, allowing attackers to manipulate discovery, s…

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 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 SkillGuard-Robust, a novel framework for robust, cross-file security auditing of untrusted agent skills, achieving high accuracy on large-scale package evaluations.

This paper presents HarmfulSkillBench, a large-scale benchmark demonstrating that even small percentages of publicly available skills can be misused for harmful actions, significantly lowering LLM ref…

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…