HarnessAudit audits full execution trajectories of LLM agents for boundary compliance and introduces HarnessAudit-Bench showing that task completion often diverges from safe execution with risks accumulating over longer trajectories.
Native runs (Claude Code, Codex, OpenClaw) emit native session artifacts that are collected and ingested after the run terminates
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Auditing Agent Harness Safety
HarnessAudit audits full execution trajectories of LLM agents for boundary compliance and introduces HarnessAudit-Bench showing that task completion often diverges from safe execution with risks accumulating over longer trajectories.