agent-harness

Warn

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The loop controller script executes arbitrary shell strings retrieved from a JSON state file using subprocess.run(shell=True).
  • Evidence: proc = subprocess.run(chk["cmd"], shell=True, cwd=args.cwd, capture_output=True, text=True, timeout=CHECK_TIMEOUT_S) in scripts/loop_controller.py.
  • Context: This mechanism is the core of the 'verify' command, which adjudicates task completion by running machine-readable checks defined in a domain manifest.
  • [REMOTE_CODE_EXECUTION]: The system's architecture relies on executing arbitrary commands stored in data files (plan.json and state.json). An attacker who can influence the content of these files (e.g., via indirect injection into the goal compiler or supply chain tampering) can achieve local code execution.
  • Context: The skill documentation in references/verification_discipline.md acknowledges this risk, explicitly labeling plan and state files as a 'trust boundary' and warning against running the harness on files from untrusted input.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 19, 2026, 10:56 PM
Security Audit — agent-trust-hub — agent-harness