cms-paywall-audit

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from external CMS articles.
  • Ingestion points: Data is pulled from the CMS via cms_list_articles, cms_get_article, and cms_list_article_paragraphs (SKILL.md).
  • Boundary markers: There are no instructions to use delimiters or ignore embedded commands within the article content being audited.
  • Capability inventory: The primary workflow is limited to read-only tools (cms_list_*, cms_get_article), which mitigates the risk of unauthorized actions, though write-access tools like cms_update_article are present in the broader environment.
  • Sanitization: The skill does not perform sanitization or filtering on the retrieved article text before processing it for the audit report.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 02:57 PM
Security Audit — agent-trust-hub — cms-paywall-audit