InfoResearchPreprintLLM-specific
Can Benign Skills Induce Misaligned Behavior in LLM Agents?
- Published
- Record updated
Summary
This study examines whether benign reusable skills can make LLM agents execute unsafe external actions, a risk the authors call skill-induced behavioral misalignment. Across five LLM backbones and three benchmarks, skill augmentation raised benign task accuracy by 10.3 percentage points and also raised the unsafe action rate by 10.3 pp, including with expert-curated skills. A paired trajectory analysis found 24 of 50 newly unsafe trajectories did not complete the harmful objective.
Mitigation
A guard that checks proposed tool actions before execution reduces violations while retaining gains on benign tasks.