prd-to-goal

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime reads outsider-authored free text from GitHub issue bodies (gh issue view <N> --json title,body,labels → body) or from spec files/PRD text provided by the user, and that text is then used to generate the /goal assertions that are fed into the agent’s LLM context.