prd-breakdown

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches public, user-generated PRDs via "gh issue view " in Phase 1 and also authorizes WebSearch/WebFetch in Phase 2, and it directly parses and acts on that external content to drive slicing, issue drafting, and GitHub actions, so untrusted third-party content can influence agent decisions and tool use.