arXiv (All)
open access
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
artificial-intelligencecomputation-and-languagecryptography-and-securitymachine-learningmultiagent-systems
Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces that are largely missed by existing safety evaluations: even w
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces#783571
- SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces#178796
- SkillDRE: Dual-Stage Red-Team Evolution of Agent Skills via Pre-Execution and Runtime Feedback#1116731
- SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation#1141860
- AgentAudit: An Open, Extensible Framework for Full-Lifecycle Trust Evaluation of AI Agents#996690
Record · ID 785161
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive