gateguard

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

• Third-party content exposure detected (medium risk: 0.65). GateGuard’s required runtime workflow performs Grep/Read to “List ALL files that import/require this file” and to “show field names, structure, and date format,” which ingests repository text authored by other parties (e.g., existing code/docs in the codebase) into the LLM context, creating an indirect prompt-injection surface from outsider-authored free text.