ClawAudit verdict

wechat-tietu-draft

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

Creates image-focused WeChat Official Account draft articles by automating the WeChat web editor via CDP browser control on the user's own logged-in session; execution sink is a documented Python script.

⚠ 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.

48
security
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (6)

Pattern match high

Possible hardcoded credential

skill_main.py · prose · downgraded · token=" in u.lower(): return p if best is None:

Pattern match medium

subprocess execution — runs system commands from Python

skill_main.py · prose · downgraded · subprocess.run(

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

skill_main.py · prose · downgraded · http://127.0.0.1

Pattern match low

Opens WebSocket connection

SKILL.md · prose · downgraded · WebSocket

Pattern match low

Python urllib.request — network access

skill_main.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

skill_main.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?

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