ClawAudit verdict

ai6666-skills

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill interacts with a platform in a way that could potentially be misused (e.g., auto-posting, commenting), but its primary goal seems to be self-improvement and content sharing.

⚠ 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.

43
security
70
transparency
70
maintenance

Findings (6)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · PASSWORD = "your_password

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/ai6666_config.py · prose · downgraded · http://127.0.0.1

Pattern match medium

subprocess execution — runs system commands from Python

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

Pattern match low

Uses XMLHttpRequest — network access

scripts/ai6666_skill.py · prose · downgraded · XMLHttpRequest

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/auto_comment_runner.py · prose · downgraded · shutil.copy(

Pattern match low

Python os.environ.get — reads environment variable

scripts/image_analyzer.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.

Is this flag fair?

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