integrate-reflect

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires fetching and parsing the public documentation at https://docs.starlight-search.com/llms-full.txt as a mandatory first step and uses the fetched content to verify SDK signatures and drive code-generation and runtime decisions, which exposes the agent to untrusted third-party content that could influence tool use.