OpenAI patches ChatGPT vulnerability allowing unauthorized agent creation
The AgentForger flaw allowed attackers to create and remotely control invisible autonomous AI agents within victim organizations. OpenAI has since implemented a fix for the vulnerability.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Pokee-Isaac 28B V0 offers 10M-token context and tool use
- Goodfire Silico helps frontier AI research on vision models
- Codex creates CAD design for lost coffee grinder lid
- Not Diamond launches Code model router for coding agents
- Opus 4.8 quality at half the cost touted for agent infrastructure