cms-place-publish

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a secure mutation workflow by requiring a 'Preview (dry-run)' step and 'explicit confirmation' before any tools that modify data are executed.
  • [SAFE]: Input validation is enforced for sensitive parameters, specifically requiring finite decimal coordinates and forbidding the agent from guessing location data.
  • [SAFE]: The skill uses a least-privilege approach by specifying a READ_WRITE access contract and restricting scheduling logic to specific status states.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content (text, quotes, embeds) to populate CMS fields. While this creates an entry point for untrusted data, the risk is mitigated by the mandatory manual confirmation step which allows the user to review the final payload before it is committed to the CMS.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 02:57 PM
Security Audit — agent-trust-hub — cms-place-publish