plan-design-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 directs the agent to perform external web searches ("Search Before Building" / "WebSearch fallback") and even to open an external URL in the preamble (open https://garryslist.org/posts/boil-the-ocean), which indicates the skill will ingest public third‑party content and use those results as inputs to decision-making.