ClawAudit verdict

daily-maoxuan-article

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

The skill generates AI-analyzed articles from a local dataset and pushes them to user-controlled Telegram and Obsidian endpoints; the publisher note confirms prior hardcoded-key issues were resolved in v9.0.1/9.0.2, and all current behavior matches the transparent daily-push purpose.

⚠ 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.

53
security
100
transparency
90
maintenance

Findings (5)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · TOKEN="your-bot-token

Pattern match medium

subprocess execution — runs system commands from Python

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

Pattern match low

Python urllib.request — network access

scripts/daily_article_final.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

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

Pattern match low

Python httpx request — network access

scripts/deep_gen.py · prose · downgraded · httpx.post(

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