gsd-plan-phase

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime path ingests outsider-authored free text when it performs research by fetching/reading external sources (e.g., public web pages or other non-user documents) and then passes that readable text into the LLM context for planning/verification via the research→plan→verify loop.