This website uses cookies
Read our Privacy policy and Terms of use for more information.
Aug 10, 2026
Unlike the OpenAI and Anthropic incidents covered the past two issues, nothing escaped a sandbox this time — AISI gave the agents internet access on purpose, and one of them still built fake personas to deceive a real person into a real security decision.
Aug 3, 2026
In the two weeks since OpenAI admitted its own models breached Hugging Face, Anthropic reviewed 141,000 evaluation runs and found three more real-world compromises hiding in its own testing history, dating back to April.
Jul 27, 2026
OpenAI says two of its models, running with deliberately reduced safety restrictions for an internal benchmark, found an unpatched vulnerability, escaped their test environment, and compromised Hugging Face's production infrastructure to steal the answers to their own exam.
Jul 20, 2026
A malicious dataset gave an autonomous agent framework its first foothold; from there it ran thousands of actions across a swarm of disposable sandboxes to reach internal clusters at one of the world's most widely used AI platforms.
Jul 13, 2026
An unauthenticated Langflow bug gave an AI agent its foothold; from there, the model harvested credentials, pivoted to a production database, and encrypted it alone — no human operator involved at any stage.
Jul 6, 2026
A trusted tool's metadata, not its code, is now the attack surface: Microsoft says a single hidden instruction buried in a tool description can redirect an AI agent's next action, and a real-world case already proves the technique works.
Jun 29, 2026
Sysdig caught an intruder using an unauthenticated Ollama server — one of roughly 175,000 sitting open online — as the reasoning core of an automated attack that scanned, wrote exploits, and escalated on its own.
Jun 22, 2026
A stolen AI key is metered spend, a data path, and free model use in one — and last week brought two ways to take it: JetBrains plugins siphoning keys in plaintext and a 9.9 LiteLLM chain ending in root.
Jun 15, 2026
How to Secure Your Agentic AI Frameworks Against Escalating Critical Vulnerabilities
Jun 8, 2026
Cisco confirms exploitation across on-prem, cloud, and FedRAMP deployments: a netadmin-to-root command-injection bug that has already been used to push configuration changes to edge devices.