ClawAudit verdict
cnblogs-publisher
Blog management skill that uses MetaWeblog API with user-configured credentials stored in environment variables; executionSinkDetected is present but all commands are standard Python script invocations for the documented blog publishing workflow.
⚠ 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.
Findings (5)
Possible hardcoded credential
SKILL.md · code · TOKEN="your-metaweblog-token
Pipe to python — executes piped content as Python code
README.md · prose · downgraded · | Python
Accesses shell history/config
README.md · code · ~/.zshrc
Python os.getenv — reads environment variable
scripts/delete_post.py · prose · downgraded · os.getenv(
Python http.client — stdlib network access
scripts/delete_post.py · prose · downgraded · http.client.HTTPSConnection
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class F). 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?
Thanks — recorded.