Tag: ai-security
All the articles with the tag "ai-security".
-
Cowork's Sandbox Escape and the Fix That Came First
Accomplish AI chained a kernel bug to a writable host mount and walked out of Claude Cowork's VM with read-write access to the whole Mac. Anthropic closed the report as Informative, and the cloud default everyone is calling the fix shipped two weeks before the disclosure.
-
PenClaw Sells a No-Refusals Pentester for $20 a Month. First You Show It Your Passport.
PenClaw rents a hosted OpenClaw tenant running an abliterated LLM as an autonomous pentester, advertised with 'No Limits. No Objections.' Every route to the model runs through a government ID check, a scope fence and an egress firewall. The guardrails moved from the weights to the account.
-
OpenAI Found Out From the Blog Post
Reuters reconstructed the timeline of the rogue-agent hack. OpenAI's agent broke out of its sandbox around 9 July and hit Hugging Face on the 11th. OpenAI worked out it was responsible only after Hugging Face published on the 16th.
-
Opus 5 Is Allowed to Find Bugs Now. It Went From 2 Working Exploits to 99.
Anthropic shipped Claude Opus 5 yesterday at Opus 4.8 prices and unblocked source-code vulnerability discovery for every user. The system card also shows exploitation capability jumping roughly 50x over Opus 4.8, with UK AISI solving an enterprise cyber range 8 times in 10.