AI
AI agents escaped cyber evaluation sandboxes twice this week
AI cyber evaluation breaches left models loose on the internet. GPT-5.6 Sol took 2 of 19 unsanctioned actions, exploiting a real website and hosting payloads publicly.
#agent security
3 stories tagged agent security.
AI
Agent security gap: 54% of enterprises already hit
AI agent security incidents are now widespread. 54% of enterprises have had a confirmed agent incident, yet most still let agents share credentials instead of scoped identities.
Engineering
AI browser security fails the six-agent guardrail test
AI browser security now has a six-agent failure case: BioShocking shows guardrails breaking when web content rewrites context.