ClawAudit verdict
ghost-publishing-pro
Headless Ghost CMS publishing with explicit execution gates (credential check, fetch-before-put, publish confirmation); all operations target the user own Ghost instance.
⚠ 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
network_out
package_install
Findings (5)
<script> tag in markdown — potential code injection
references/api.md · code · <script>
Instructs covert action — may act without user awareness
SKILL.md · code · silently
Pipe to python — executes piped content as Python code
references/workflows.md · prose · downgraded · | python3
Node http/https module — low-level network access
references/workflows.md · prose · downgraded · require('https')
Python urllib.request — network access
references/workflows.md · prose · downgraded · urllib.request
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outnetwork_inpackage_install Is this flag fair?
Thanks — recorded.