contentful

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs several official Node.js packages for Contentful integration, including 'contentful', 'contentful-management', and rich text rendering utilities. These originate from a well-known service and are used according to standard implementation patterns.
  • [PROMPT_INJECTION]: The skill fetches and processes structured content from the Contentful API, which constitutes an indirect prompt injection surface.
  • Ingestion points: The agent retrieves content using 'getEntries' and 'sync' methods as documented in 'SKILL.md'.
  • Boundary markers: No explicit instructions or delimiters are provided to ensure the agent ignores potential instructions embedded within the CMS content.
  • Capability inventory: The skill leverages network access for API interactions and local file system access for asset management ('fs.createReadStream').
  • Sanitization: The implementation uses '@contentful/rich-text-react-renderer', which is the standard method for safely processing Contentful rich text.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:52 AM