threat-model-generation

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

• Third-party content exposure detected (high risk: 0.70). The required workflow scans the target repository (and optionally an existing .factory/threat-model.md) and then generates a natural-language threat model from that codebase content, which can include outsider-authored free text (e.g., repository files not authored by the operating user) that becomes LLM-readable context during analysis.