meme-and-culture

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow explicitly treats “a trend/screenshot/web result read to react to” as content the agent evaluates, which implies runtime ingestion of outsider-authored free text (e.g., scraped web results or screenshots) into the LLM context, creating an indirect prompt-injection risk.