SkillHarm benchmark shows current AI agents are vulnerable to lifecycle-aware skill poisoning with success rates up to 86.3% for fixed-payload attacks and 69.3% for self-mutating attacks.
Coding Agents with Multimodal Browsing are Generalist Problem Solvers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction
SkillHarm benchmark shows current AI agents are vulnerable to lifecycle-aware skill poisoning with success rates up to 86.3% for fixed-payload attacks and 69.3% for self-mutating attacks.