cloudflare

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests untrusted user-generated content from HTTP requests (e.g., "Example 2: AI-Powered Content Moderation" in SKILL.md and the Vectorize/indexing examples in references/examples.md), passes that content to env.AI.run and other processing, and then uses the analysis to accept/reject, store, or route data—so third-party content can materially influence behavior.