ClawAudit verdict

has-anonymizer

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Downloads a GGUF model from HuggingFace and runs local inference via llama-server for on-device text/image anonymization; all capabilities match the stated privacy-preserving anonymization purpose with no exfiltration.

⚠ 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.

63
security
90
transparency
70
maintenance

Findings (6)

Pattern match medium

Instructs covert action — may act without user awareness

SKILL.md · prose · downgraded · silently

Pattern match medium

subprocess execution — runs system commands from Python

references/eval/eval.py · prose · downgraded · subprocess.run(

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/has_text/client.py · prose · downgraded · http://127.0.0.1

Pattern match low

Python shutil file operation — copies/moves/deletes files

references/eval/eval.py · prose · downgraded · shutil.rmtree(

Pattern match low

Python os.environ.get — reads environment variable

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

Pattern match low

Python urllib.request — network access

scripts/has_text/server_runtime.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.

Is this flag fair?

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