pith. machine review for the scientific record. sign in

Depending on the test case, the agent encounters adversarial content through exactly one of the three injection vectors

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

ClawSafety: "Safe" LLMs, Unsafe Agents

cs.AI · 2026-04-01 · unverdicted · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • ClawSafety: "Safe" LLMs, Unsafe Agents cs.AI · 2026-04-01 · unverdicted · none · ref 13

    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.