More on the OpenAI Agent’s Attack on Hugging Face

Hugging Face has published a detailed timeline of the attack. From the summary: The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting software vulnerabilities. OpenAI ran this on its own...

The OpenAI Hack Shows the Genie Is Out of the Bottle

This essay originally appeared inForeign Policy. Earlier this month, two of OpenAI's models broke out of their containment sandbox and attacked another AI company. The story is kind of wild. OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost...

The OpenAI and Anthropic AI Hacking Sprees Are a Messy New Legal Frontier

Both major AI labs’ models broke containment, escaped onto the internet, and hacked other companies. If a human had done that, the law would likely be against them. But a bot?...

promptfoo v0.121.20

Promptfoo: LLM evals & red teaming promptfoo is a CLI and library for evaluating and red-teaming LLM apps. Stop the trial-and-error approach - start shipping secure, reliable AI apps. Website · Getting Started · Red Teaming · Documentation · Discord Promptfoo is now part of OpenAI. Promptfoo...

EUVD-2026-50468

Flyto2 Core: LLM/API keys leak to an attacker-controlled baseurl...

Flyto2 Core: LLM/API keys leak to an attacker-controlled base_url

Summary llm.chat reads the operator's provider key from the environment OPENAIAPIKEY, ANTHROPICAPIKEY, ... and sends it in the Authorization: Bearer header to baseurl, a parameter the caller controls. baseurl is only checked against the SSRF guard, and the guard allows any public host, so pointin...

OpenAI’s Hacking Debacle Comes Down to Human Error

If the generative AI giant had followed well-known security best practices, it’s likely that its AI agent would never have escaped to the open internet and hacked multiple companies...

CVE-2026-67425

Flyto2 Core is an execution kernel for automation and AI-agent workflows. Prior to 2.26.6, llm.chat reads provider keys such as OPENAIAPIKEY and ANTHROPICAPIKEY from the environment and sends them in the Authorization: Bearer header to caller-controlled baseurl, allowing an attacker to receive th...

CVE-2026-67425 Flyto2 Core: LLM/API keys leak to an attacker-controlled base_url

Flyto2 Core is an execution kernel for automation and AI-agent workflows. Prior to 2.26.6, llm.chat reads provider keys such as OPENAIAPIKEY and ANTHROPICAPIKEY from the environment and sends them in the Authorization: Bearer header to caller-controlled baseurl, allowing an attacker to receive th...

Measuring the Tendency of AI Agents to Go Rogue

This essay was written with Barath Raghavan, and originally appeared inThe Guardian. In July, Hugging Face, a company that hosts much of the world's AI software and open-source AI models, was hacked. A malicious dataset had been used to run code on one of its servers. Whoever was behind it captur...

OpenAI Agent Used Exposed Credentials Across Four Services During Hugging Face Breach

OpenAI on Tuesday revealed the rogue artificial intelligence AI agent that escaped its sealed evaluation environment and broke into Hugging Face's production environment also hacked multiple third-party accounts and services as part of the attack. The latest disclosure shows that the security...

CVE-2026-51263

Rejected reason: DO NOT USE THIS CVE RECORD. ConsultIDs: none. Reason: This record was withdrawn by its CNA. Further investigation showed that it was not a security issue. Notes: none...

JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breach

JFrog has confirmed that OpenAI models exploited a zero-day in self-hosted Artifactory while trying to reach the open internet from a sealed evaluation environment. Artifactory is JFrog's software repository manager. OpenAI says the models then escalated privileges and moved laterally until they...

PT-2026-65506

schreibfaul1 ESP32-audioI2S 3.4.5 is vulnerable to Buffer Overflow. The Audio::openai speech function in the Audio library manually constructs JSON request bodies and HTTP request headers by directly concatenating externally controllable input and instructions strings without effective length...

CVE-2026-51263

...

CVE-2026-51263

...

CVE-2026-51263

CVE-2026-51263 entry is rejected/not used per the initial description.

EUVD-2026-49863

schreibfaul1 ESP32-audioI2S 3.4.5 is vulnerable to Buffer Overflow. The Audio::openaispeech function in the Audio library manually constructs JSON request bodies and HTTP request headers by directly concatenating externally controllable input and instructions strings without effective length...

A week in security (July 20 – July 26)

Last week on Malwarebytes Labs: Don’t get fooled by TikTok resin art scams Call of Duty Mobile scam uses fake free points to steal player accounts OpenAI’s agent escaped its sandbox during a security test Google wants to store a selfie video of your face Beyond the Play Store: How Android threats...

The OpenAI Models That Hacked Hugging Face Were ‘Active on the Internet’ for Days

Plus: Russian hackers are trying to steal US nuclear scientists’ emails, the State Department bans known scammers from entering the United States, and more...