ClawAudit verdict
updating-openrouter-free-models
Fetches OpenRouter model lists, tests availability via API, and updates local config files; executionSinkDetected is from documented script commands consistent with the legitimate purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
file_read
agent_memory
Findings (6)
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/openclaw.json
Possible hardcoded credential
complete_test.sh · prose · downgraded · TOKEN="${ANTHROPIC_AUTH_TOKEN:-YOUR_ANTHROPIC_API_KEY}
References child_process — can spawn system processes
INSTALLATION.md · code · child_process
Pipe to python — executes piped content as Python code
INSTALLATION.md · prose · downgraded · | Python
subprocess execution — runs system commands from Python
fetch_models.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
test_models.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
file_readagent_memory Is this flag fair?
Thanks — recorded.