effect

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

• Third-party content exposure detected (high risk: 0.90). This skill's "Source Of Truth" instructions explicitly require cloning and reading the public GitHub repository at https://github.com/Effect-TS/effect-smol into .opencode/references/effect-smol and searching that third-party content for APIs/examples before answering or implementing, which exposes the agent to untrusted external content that can influence its decisions and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs cloning and using https://github.com/Effect-TS/effect-smol at runtime (into .opencode/references/effect-smol) and requires inspecting that fetched repo to drive answers/implementations, so the external content can directly influence agent prompts and behavior.