to-spec-plus

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

• Third-party content exposure detected (high risk: 0.70). This skill’s required workflow (“take the current conversation context and codebase understanding”) relies on the existing conversation context produced by prior steps (e.g., grill-me-plus), which is outsider-authored free text from other participants, and that context is then synthesized into the LLM prompt for spec writing.