cloudflare-workers-security

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly fetches and consumes external, potentially untrusted web resources as part of its workflow (e.g., references/authentication.md's verifyIdToken fetches a jwksUrl, the OAuth code fetches tokenUrl, and scripts/security-audit.sh/cors checks fetch arbitrary target URLs), and those fetched responses are parsed and used to make authentication and audit decisions that can materially change behavior.