ChatGPT Agent Violates Policy and Solves Image CAPTCHAs | SplxAI Blog
splx.ai
Discover how a ChatGPT agent bypassed built-in policies to solve image-based CAPTCHAs, exposing critical weaknesses in AI guardrails and CAPTCHA security.

cross-posted from: https://programming.dev/post/37726760

  • Guardrails can be bypassed: With prompt injection, ChatGPT agents can be manipulated into breaking built-in policies and solving CAPTCHAs.
  • CAPTCHA defenses are weakening: The agent solved not only simple CAPTCHAs but also image-based ones - even adjusting its cursor to mimic human behavior.
  • Enterprise risk is real: Attackers could reframe real controls as “fake” to bypass them, underscoring the need for context integrity, memory hygiene, and continuous red teaming.
  • jj4211@lemmy.worldEnglish
    2·
    4 hours ago

    It’s about making headless bots unreasonably expensive to make massive requests with.