effect-ts

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Tool Use" and "AI Integration" documentation explicitly shows creating tools that call public APIs (e.g., https://icanhazdadjoke.com) and wiring external LLM providers (OpenAI, Anthropic) whose responses are ingested via LanguageModel.generateText and tool handlers, so untrusted third‑party content is fetched and fed into the agent's workflow.