The paper introduces SafeClawArena, a 406-task benchmark evaluating security failures in three Claw-like agent platforms across skill supply-chain, state exploitation, data flow, and prompt injection surfaces.
AgentHarm: A benchmark for measuring harmfulness of LLM agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
The paper introduces SafeClawArena, a 406-task benchmark evaluating security failures in three Claw-like agent platforms across skill supply-chain, state exploitation, data flow, and prompt injection surfaces.