creating-releases-json

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow includes fetching and parsing live web content (e.g., “Fetch the live URL” / “fetch it, or check it against the codebase/site” in Step 2/5), which can be outsider-authored free text that the agent may read and include in its LLM context.