ai-native-assessment

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

• Third-party content exposure detected (high risk: 1.00). The required runtime workflow reads outsider-authored free text from the target repository itself (e.g., AGENTS.md, CONTRIBUTING.md, README.md, docs/**, and representative src files) into the LLM context during Phase 2 “LLM reads actual code and content” and Category 6 scoring.