translation-creative

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via the user-supplied source (ad copy/headline/marketing brief string or text file) that is then fed into the DRAFT/REFLECT/IMPROVE core loop; this text is not authored by the operating user by definition of “outsider” in the prompt.