ClawAudit verdict
juejin-skills
Juejin tech community skill with explicit network allowlists (juejin.cn, api.juejin.cn), filesystem path validation, and draft-only publishing policy; the content documents security controls rather than bypassing them.
⚠ 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 (7)
Accesses cloud provider credentials
SKILL.md · frontmatter · ~/.aws
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
<script> tag in markdown — potential code injection
juejin_skill/downloader.py · prose · downgraded · <script>
Accesses .ssh directory
SKILL.md · prose · downgraded · .ssh/
Python os.environ.get — reads environment variable
juejin_skill/config.py · prose · downgraded · os.environ.get(
Python httpx request — network access
juejin_skill/downloader.py · prose · downgraded · httpx.get(
Popular HTTP library — network access
run_publish.py · prose · downgraded · Got
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.