cms-draft-review
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a strict
READ_ONLYaccess contract. It is designed to surface information about CMS drafts (articles, events, maps, and videos) using specific discovery and retrieval tools without the ability to update, publish, or delete content. - [SAFE]: The workflow follows a predictable and restricted sequence of tool calls (
cms_list_cms_sections,cms_list_articles, etc.) focused entirely on internal CMS data, with no evidence of network exfiltration or unauthorized file system access. - [SAFE]: Guardrails are explicitly defined to prevent the agent from performing destructive actions, such as deleting drafts, even those categorized as 'Abandoned'.
Audit Metadata