For months, OpenAI’s agent swarms have been attacking online databases to find obscure facts
OpenAI Says Misaligned AI Agents Hacked Hugging Face and Bypassed Security Controls
OpenAI pauses training of its ‘most capable models’
OpenAI's AI agents accidentally uploaded user-provided images to third-party sites
2 min
OpenAI agent hacked Australian government website, PM says
Unsecured OpenAI agents posted 53 user images on the internet without the lab’s knowledge
in the wild 3 min1
Revealing the details of how OpenAI agents hacked Hugging Face
in the wild 15 min
AI Sandbox Escapes: Why Forensic Readiness Matters More Than Containment
Meta makes the Muse filesystem even more accessible
2 sources 2 min
Muse sure looks a lot like OpenClaw
4 sources 5 min
With the Rise of AI Agents, SOC 2 Should Adapt or Risk Irrelevance
8 min
Salmon Introduces Execution Verification Infrastructure (EVI) for Securing AI Agents and Autonomous Systems
2 sources 4 min
Docker introduces OCI-based Kits to package agents and their guardrails
5 min
Stop watching what AI agents say and start watching what they do
5 min
LLM Agents Can Easily Tamper With Their Own Traces
Muse will apparently let you download its entire filesystem
3 min
Cloud Range lets SOCs benchmark AI agents against human defenders
3 min
What to do first when you get 90 days to secure AI agent data
5 min
Outerlimit Raises $16M to Build Zero Trust Security Layer for Autonomous AI Agents
2 sources 3 min
Meta’s Muse AI Assistant Rolled Out With a Serious Security Flaw
Prismor: Open-source runtime control plane for AI agents
2 min
A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem
How Meta's Muse works, revealed by the 6.8 GB filesystem it sent me
7 min
Who signed off on that AI agent? Nobody? Thought so.
7 min