ClawAudit verdict
endpoints
45
🟠 Risky
Significant concerns — only install if you understand the risks
The skill makes API calls to an external service which could potentially be used for data exfiltration, but the provided content seems to be focused on document management.
⚠ 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.
93
security
70
transparency
70
maintenance
Permission integrity
Installs packages at runtime — transitive dependencies are not auditable
package_install
Findings (1)
Pattern match low
Accesses sensitive environment variables
scripts/src/index.ts · prose · downgraded · process.env.ENDPOINTS_API_KEY
Permissions & capabilities
No declared permissions — minimal attack surface.
package_installnetwork_in Is this flag fair?
Thanks — recorded.