Caveat verdict

clawtraces

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill accesses credentials and may potentially exfiltrate sensitive data, although its primary purpose seems legitimate.

⚠ 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.

68
security
60
transparency
70
maintenance

Findings (7)

Pattern match medium

subprocess execution — runs system commands from Python

scripts/cli.py · prose · downgraded · subprocess.run(

Pattern match medium

Instructs covert action — may act without user awareness

scripts/lib/adapters/claude_code/discover.py · prose · downgraded · silently

Pattern match low

Python os.environ.get — reads environment variable

scripts/env_check.py · prose · downgraded · os.environ.get(

Pattern match low

References agent configuration files

scripts/lib/adapters/claude_code/_workspace.py · prose · downgraded · CLAUDE.md

Pattern match low

Popular HTTP library — network access

scripts/lib/adapters/hermes/harness.py · prose · downgraded · got

Pattern match low

References agent memory files

scripts/lib/adapters/openclaw/harness.py · prose · downgraded · MEMORY.md

Pattern match low

Python urllib.request — network access

scripts/lib/core/auth.py · prose · downgraded · urllib.request

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.

network_incredential_access

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API