effectts

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md's required "Research First (ALWAYS)" workflow explicitly instructs the agent to fetch and read public third‑party sources (e.g., cloning https://github.com/Effect-TS/effect and querying the Effect MCP / https://effect.website/docs) which the agent is expected to interpret and use to guide code and layer decisions, exposing it to untrusted user-generated web content that could inject instructions.