navigate-skills

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Protocol Health Check" explicitly instructs the agent to verify protocol health using live public sources (e.g., DefiLlama REST API https://api.llama.fi/ or web search), which requires fetching and interpreting untrusted third-party web content that can directly change recommendations and next actions.