improve-skill

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

• Third-party content exposure detected (high risk: 0.70). The skill's Phase 2b Live Doc Validation explicitly instructs the agent to "Use WebSearch or WebFetch against official documentation" for third-party claims, meaning the agent will fetch and read open/public web content (external docs, npm/APIs/CLIs) which it then uses to verify claims and influence its decisions — exposing it to untrusted third‑party pages that could carry indirect prompt injections.