Caveat verdict
wechat-mp-auto
WeChat Official Account automation skill orchestrating AI-driven content pipeline (research, draft, image, publish); credential_access is for the WeChat API key as documented, and all behavior matches the stated content-publishing purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
credential_access
Findings (6)
Possible hardcoded credential
README.md · code · SECRET="your_app_secret
<script> tag in markdown — potential code injection
CHANGELOG.md · prose · downgraded · <script>
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/.env
Python os.environ.get — reads environment variable
src/config.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
src/publish.py · prose · downgraded · urllib.request
Base64 encoding/decoding
src/skills/image_generator.py · prose · downgraded · Base64Encode
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.
credential_access Is this flag fair?
Thanks — recorded.