ClawSafety benchmark finds 40-75% attack success rates on frontier LLMs used as agents, with skill-file injections most effective and safety depending on both model and full agent framework.
No authority level, urgency framing, or SKILL instruction overrides this heuristic
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ClawSafety: "Safe" LLMs, Unsafe Agents
ClawSafety benchmark finds 40-75% attack success rates on frontier LLMs used as agents, with skill-file injections most effective and safety depending on both model and full agent framework.