Evasion: Response Priming via Forced Affirmative Opener - ATR-2026-01016 (48ce5c83-5adc-5858-81ec-24b4d7e3dc3e)
Detects prompt injection where the attacker instructs the model to begin its response with a pre-defined affirmative phrase ("Sure!", "Absolutely! Here's", "I would be happy to help", "Of course!") before answering. Starting with an affirmative opener suppresses the model's natural tendency to generate a refusal and primes the response trajectory toward compliance. Distinct from refusal-suppression (ATR-2026-01015) which bans specific words; this pattern mandates an opener that semantically commits the model to proceed. The combination of forced affirmative opener + a harmful follow-on request is the attack carrier.