Claude Code auto mode becomes default, blocking 89% of harmful actions vs humans' 13.6%
“In this evaluation, none of the 720 attack attempts succeeded against Claude Fable 5, Opus 5, or Sonnet 5 running auto mode.”
agentic-security
8 tracked signals on agentic-security.
A regulated CFD broker deployed agentic AI cyber defense in production to counter autonomous AI-driven attacks.
“I won't downplay the threat. It is real. Uh, and if you're not responding to it effectively, it is existential.”
Snyk's agentic security framing expanded from generated code to agent access and actions
“our customers started telling us that they were not only worried about the code that was being generated, they were also worried about what the agent had access to and then also the actions the agent might be taking”
AI-accelerated coding multiplies security vulnerability surface by 10x or worse
“if everyone's shipping code at 10 times faster and the defect rate stays the same, the vulnerability rate then that doesn't that mean that the defect surface goes up by 10x?”
Apple details security techniques and APIs to mitigate prompt-injection risks in LLM-powered agentic app features.
“LLM's introduce a new probabilistic engine within your application that is both powerful but risks being tricked.”
Serval uses coding agents to challenge ServiceNow in enterprise IT automation
“Serval is a fuse. We are a way for a large enterprise with a bunch of rules, approvals, processes, and policies to safely and comfortably implement these tools at scale.”
AI agents with legitimate permissions create a new high-velocity enterprise security threat category
“the same type of threat is coming from non-human actors, agents that essentially have legitimate access to the environment with legitimate permissions”
Snyk launched a dedicated AI security track at AI Engineer World's Fair to address a gap
“Security needs to be very much part of the room.”