ClawAudit verdict
creative
xpr-creative
The skill provides creative deliverable tools for AI agents and does not exhibit any malicious or deceptive behavior.
⚠ 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 (3)
Uses exec() — may execute shell commands
src/index.ts · prose · downgraded · exec(
Data URI with base64 payload — may embed malicious content
src/index.ts · prose · downgraded · data:application/json;base64,
Accesses sensitive environment variables
src/index.ts · prose · downgraded · process.env.GITHUB_TOKEN
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.