arXiv cs.AIPaper
Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents
This flips the security model for skill-augmented agents from "vet skills before install" to "guard skills at runtime." SkillSonar lets you add, edit, and inspect your own protections without modifying the agent runtime. If you're building agents that load untrusted skills, this is the pattern to adopt now—the attack surface is real, as SCOPE-R confirms.