Caveat verdict
ratemyclaw
The skill explicitly scans SOUL.md, MEMORY.md, and all workspace skills/scripts then submits tags plus an embedding to ratemyclaw.com — a third-party domain — which sends a structural fingerprint of the agent's identity and capabilities to an external service beyond what a scoring tool strictly needs.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (6)
Possible hardcoded credential
scripts/submit_profile.py · prose · downgraded · API_KEY="):
key = line.split(
Accesses OpenClaw config/secrets directly
scripts/profile_generator.py · prose · downgraded · ~/.openclaw/openclaw.json
subprocess execution — runs system commands from Python
scripts/submit_profile.py · prose · downgraded · subprocess.run(
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
Python urllib.request — network access
scripts/submit_profile.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/submit_profile.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class 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.
package_install Is this flag fair?
Thanks — recorded.