Latest security news

Manifold Security has disclosed eight security flaws across seven command-line AI coding agents in which a repository's own Git configuration names a command that the agent runs on the developer's machine, four of them still unpatched at publication. The command executes as the user, outside the agent's sandbox and without an approval prompt, and exploitation requires the repository to arrive

Don’t panic if you spot an illegally created image or video of you online – there are ways to request its removal

Security ... this time it will be different

A threat actor used a variety of infostealers to collect session information and access Claude accounts belonging to an unknown number of users.

One of my internet-exposed inference honeypots was discovered, relabeled with sought-after model names, and incorporated into infrastructure apparently used to provide "free" LLM backends. It then received a real coding-agent session — history, filesystem output, working paths, and the agent's local tool manifest. The honeypot did not request or cause any tool execution; what the request exposed is what a malicious operator in that position could do.

OpenAI's Hugging Face attack postmortem shows agents don't care about rules — they need strong controls.

Commodity malware steals authenticated sessions, letting thieves freeload on victims' paid usage

New research reveals that AI safety refusal lives in a thin neural layer, highlighting the critical need for external, multi-layered security.

More prompt-injection hijinks from wunderwuzzi