ClawAudit verdict
auto-sec-blogger
Collects public security news from Google News, arXiv, and HackerNews, generates blog posts via GLM-4.7, and publishes to Notion/GitHub Pages; all credentials are user-supplied environment variables and the workflow is transparent.
⚠ 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.
Permission integrity
package_install
Findings (6)
Possible hardcoded credential
scripts/test_mermaid_fix.py · prose · downgraded · API_KEY = "test_key
pip3 install — installs Python packages at runtime
SKILL.md · code · pip3 install
subprocess execution — runs system commands from Python
scripts/auto_publish_approved.py · prose · downgraded · subprocess.run(
Python os.getenv — reads environment variable
scripts/auto_publish_approved.py · prose · downgraded · os.getenv(
Python aiohttp session — async network access
scripts/llm_client_async.py · prose · downgraded · aiohttp.ClientSession
Popular HTTP library — network access
scripts/test_mermaid_fix.py · prose · downgraded · got
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?
Thanks — recorded.