2 citations · 4 across the 16 of their papers we have counts for
3 papers · 1 filter
LLM Agents Can Easily Tamper With Their Own Traces
Jeremy Qin, David Schmotz, Derck Prinzhorn +3
Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot ta…
Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure
David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner +3
A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propensity of LLM…
Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
David Schmotz, Luca Beurer-Kellner, Sahar Abdelnabi +1
LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized…