agent-doctor

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a diagnostic utility, scanning local configuration files (.codex/agents/ and ~/.codex/agents/) to identify syntax and logic errors in TOML files. This behavior is consistent with its stated purpose of health-checking subagents.
  • [SAFE]: The provided Python script (check_agents.py) relies exclusively on the Python standard library (including tomllib, available in Python 3.11+) and performs only read operations on the files it analyzes. It does not attempt to modify files or execute the commands it finds.
  • [SAFE]: No network activity, data exfiltration, or arbitrary code execution patterns were detected. The script checks for the existence of binaries on the system path using shutil.which to provide warnings about missing dependencies, but it does not invoke those binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 04:08 AM
Security Audit — agent-trust-hub — agent-doctor