codex-imagegen-backend

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

• Third-party content exposure detected (high risk: 0.70). The runtime workflow reads outsider-authored free text into the LLM context via the user-supplied --prompt/--prompt-file (_read_prompt), i.e., prompt is placed verbatim into the API payload as input_text.text in _payload—if that prompt file/content came from an outsider, it becomes LLM context (indirect prompt injection risk).