effect-ts

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly tells the agent to verify APIs against external public sources and lists public URLs (e.g., https://tim-smart.github.io/effect-io-ai/, https://effect.website/docs, and GitHub repos) in the "Primary Documentation Sources" and "Core Workflow"/"Agent Quality Checklist", meaning the agent is expected to fetch and interpret untrusted third‑party web content that can materially influence its code-generation actions.