AI agents can detect phishing.
-
AI agents can detect phishing. They just don’t know not to fall for it.
To address this risk, 1Password built the Security Comprehension and Awareness Measure (SCAM) to test AI models in real-world scenarios. The results:
Every model committed critical failures Some forwarded passwords to attackers Others typed real credentials into phishing pagesThe good news? A simple 1,200-word security skill dramatically reduced failures.
Now, we’re open-sourcing SCAM.
https://bit.ly/4aocmLC -
AI agents can detect phishing. They just don’t know not to fall for it.
To address this risk, 1Password built the Security Comprehension and Awareness Measure (SCAM) to test AI models in real-world scenarios. The results:
Every model committed critical failures Some forwarded passwords to attackers Others typed real credentials into phishing pagesThe good news? A simple 1,200-word security skill dramatically reduced failures.
Now, we’re open-sourcing SCAM.
https://bit.ly/4aocmLC@1password very cool! Even with the skill text added the risks still seem much too great
-
R ActivityRelay shared this topic
