ClawAudit verdict

create-colleague

colleague-skill

18
🔴 Dangerous
Reviewed by ClawAudit — concrete malicious or deceptive behavior found

The skill provides a feature to distill a colleague into an AI Skill, which could potentially be used for malicious purposes. The auto-collection of data and generation of a Work Skill + Persona raises concerns about data privacy and potential misuse.

⚠ 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.

35
security
100
transparency
90
maintenance

Findings (6)

Pattern match high

Writes to SKILL.md — self-modifying skill

SKILL.md · prose · downgraded · SKILL.md**(用 Write

Pattern match high

Possible hardcoded credential

tools/dingtalk_auto_collector.py · prose · downgraded · Secret: ").strip()

Pattern match medium

pip3 install — installs Python packages at runtime

INSTALL.md · code · pip3 install

Pattern match medium

subprocess execution — runs system commands from Python

tools/feishu_mcp_client.py · prose · downgraded · subprocess.run(

Pattern match low

Python os.environ.get — reads environment variable

tools/dingtalk_auto_collector.py · prose · downgraded · os.environ.get(

Pattern match low

Python shutil file operation — copies/moves/deletes files

tools/version_manager.py · prose · downgraded · shutil.rmtree(

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