poisoning-attacks

Tag

Cards List
#poisoning-attacks

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

Hugging Face Daily Papers · 2026-06-01 Cached

SkillHarm is a benchmark for evaluating skill-based attacks across the skill-use lifecycle, revealing high vulnerability (up to 86.3% attack success) in current AI agents and introducing automated attack construction via AutoSkillHarm.

0 favorites 0 likes
← Back to home

Submit Feedback