#indirect-prompt-injection

[ follow ]
Artificial intelligence
fromTheregister
4 days ago

Google says Chrome's AI creates risks only more AI can fix

Google will add a second Gemini-based model to Chrome as a User Alignment Critic to block malicious indirect prompt injection and veto misaligned agent actions.
Artificial intelligence
fromTheregister
1 month ago

OpenAI defends Atlas as prompt injection attacks surface

OpenAI's Atlas browser is susceptible to indirect prompt injection that allows web-embedded instructions to manipulate its ChatGPT agent and exfiltrate data.
[ Load more ]