effect-lookup

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fall back to reading source and docs from public GitHub repositories (e.g., https://github.com/effect-ts/effect and related opensrc GitHub paths), so untrusted third-party content will be fetched and interpreted as part of lookups and can influence the agent's actions.