launch-review

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to pull launch-tracker tickets and comments and to fetch public web pages (e.g., "pull ticket and comments", "If the launch hinges on a platform rule, fetch the current policy page in-session", and the option to "search the web — results will be tagged [web search — verify]"), so it will ingest third‑party web/tracker content that can influence decisions.