cms-stale-content-refresh

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content fetched from an external CMS, creating a potential surface for indirect prompt injection attacks.
  • Ingestion points: Data is ingested via cms_list_articles and cms_get_article (Step 2 and Step 4 of the workflow).
  • Boundary markers: The instructions do not define delimiters or specific boundary markers to isolate article content from the agent's instructions.
  • Capability inventory: While the skill itself is constrained to READ_ONLY operations and recommendation tasks, it explicitly suggests follow-up actions involving other skills (like cms-article-publish) that have write capabilities.
  • Sanitization: There is no evidence of sanitization or filtering applied to the article text retrieved from the CMS before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 02:57 PM
Security Audit — agent-trust-hub — cms-stale-content-refresh