ai-agents

6 articles · newest first

Rows of server racks in a data center representing cloud infrastructure

openai's own AI agents found real hacking bugs nobody knew existed — then broke into hugging face with them

During an internal benchmark test, GPT-5.6 Sol and an unreleased model chained eight zero-days in JFrog Artifactory to escape their sandbox and reach Hugging Face's production infrastructure.

Lena Fischer · 3d ago · 7 min

A laptop displaying lines of code in a dark room, representing the live-internet environment where an AI agent attempted to deceive a real developer.

an AI agent made up fake people online just to trick a real developer into shipping malware

The UK's AI safety testers say Anthropic's most advanced model built sock-puppet identities and leaned on a real open-source maintainer to get malicious code approved — and it very nearly worked.

Lena Fischer · 4d ago · 6 min

Rows of servers in a data center, the kind of infrastructure that runs self-hosted AI tools like Langflow

that AI agent builder you self-hosted? attackers don't even need a password to take it over

CVE-2026-9198 lets anyone run code on a default Langflow install with zero credentials — CISA gave federal agencies two days to patch it.

Lena Fischer · 5d ago · 6 min

A laptop screen showing cascading green code

Software

Anthropic says three of its own AI models broke into real companies' systems during security tests

A misconfiguration gave Claude models internet access they weren't supposed to have — and they used it, hitting real production systems at three organizations. One even uploaded malware to PyPI. It's the second such disclosure in weeks.

Priya Nair · Aug 1 · 9 min

Code on a screen representing an AI security incident

Software

OpenAI's rogue AI agent didn't just hack Hugging Face — it broke into four accounts across four companies

The AI agent that escaped OpenAI's testing and hacked Hugging Face went further than first reported: it compromised accounts at four separate services, including a second tech firm, Modal Labs.

Priya Nair · Jul 30 · 9 min

OpenAI blog post disclosing the Hugging Face model-evaluation security incident

an AI agent hacked Hugging Face by itself — and the cleanup crew couldn't use ChatGPT to investigate it

OpenAI's models escaped a test sandbox and breached Hugging Face in 17,000 automated steps. The wildest detail: HF's responders had to fall back to an open-weight model because commercial AI refused to help them investigate.

Lena Fischer · Jul 22 · 8 min