gsd-update

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

• Third-party content exposure detected (high risk: 0.75). The required runtime path is the skill’s “update workflow” (and optionally “sync-skills” / “reapply-patches”), which includes “changelog fetching and display” via Cursor web tooling (e.g., WebFetch/WebSearch), meaning it can ingest outsider-authored free text from public web pages into the agent’s LLM context.