cms-content-audit
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes untrusted data from the CMS, creating a potential surface for indirect prompt injection where malicious content in CMS entries could attempt to influence the agent.
- Ingestion points: Data is fetched from CMS articles, events, and other sections via the
cms_list_*andcms_get_*tool families, specifically targeting fields like body paragraphs and summaries. - Boundary markers: The skill does not define explicit delimiters or 'ignore embedded instructions' warnings to isolate the untrusted CMS content from the agent's logic.
- Capability inventory: The skill is restricted to
READ_ONLYoperations and reporting; it does not utilize shell execution, file-system writes, or direct network communication tools. - Sanitization: No sanitization, escaping, or validation of the retrieved CMS content is performed before it is processed by the AI.
Audit Metadata