ClawAudit verdict
zhihu-assistant
zhihu-assistant-skill
The skill scrapes Zhihu hot lists, generates answer drafts, and pushes them to Feishu for review. While it does not contain any malicious behavior, it does execute a script that could potentially be used for malicious purposes.
⚠ 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
modules/content_gen.py · prose · downgraded · api_key='your-api-key
subprocess execution — runs system commands from Python
main.py · prose · downgraded · subprocess.run(
pip3 install — installs Python packages at runtime
install.sh · prose · downgraded · pip3 install
References webhook/callback URL
main.py · prose · downgraded · webhook_url
Python os.environ.get — reads environment variable
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.
Is this flag fair?
Thanks — recorded.