vibe-togaf-architect

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

• Third-party content exposure detected (high risk: 0.70). The required workflow reads exploration/captures/DISCOVERY_REPORT.md (a file authored by someone other than the operating user) and the user’s NFR Q&A transcript, and then ingests that readable text into the agent to generate the /specs files—so outsider-authored free text can enter the LLM context via the discovery report file path.