SOURCE-LINKED INTELLIGENCE

SkillAtlas: An Attack Trace Library for Agent Skills

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Agent skills are reusable units for language-model agents, but their risks emerge through model decisions, user context, tool calls, and execution feedback rather than through stable signatures or a single sandbox run. Existing static, dynamic, and benchmark-style evaluations rarely preserve public evidence that can be inspected, searched, and reused. We present SkillAtlas, a hosted attack trace library that converts private agent-skill security report bundles into reviewed, redacted, and searchable public cases. The library contains 3,014 cases, 6,589 traces, 151,131 steps, 233 affected skill

Read original source ↗ Open in workspace

recordType

paper

region

Global