SOURCE-LINKED INTELLIGENCE

Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions. Such skills may leak secrets, corrupt code, bypass approvals, or stage data for exfiltration only after a concrete user task and workspace state make the unsafe action appear useful. This makes pre-install vetting insufficient and calls for runtime, task-conditioned protection. We propose Defense-as-Skill, a defense paradigm that implements the runtime guard itself as an installable, inspectable, and editable skill

Read original source ↗ Open in workspace

recordType

paper

region

Global