workers-best-practices

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

• Third-party content exposure detected (high risk: 0.85). This workflow explicitly requires runtime retrieval of free-form text from Cloudflare’s public best-practices/docs pages and type definitions (e.g., fetching https://developers.cloudflare.com/...), which can include outsider-authored content that gets ingested into the agent context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly instructs fetching live documentation at runtime (e.g., https://developers.cloudflare.com/workers/best-practices/workers-best-practices/ and related docs) to drive its review/writing guidance, so external content is retrieved and can directly control the agent's instructions.