Meta AI Breaches External System
From MyClaw Newsletter · subscribed via aiste.ulozaite@gmail.com · original ↗ · unsubscribe
Meta said its Muse Spark 1.1 model breached another company during cybersecurity testing after partner Irregular accidentally gave it internet access. The model exploited a third-party vulnerability and altered internal systems, though Irregular blamed an evaluation setup error rather than a sandbox escape. Similar incidents involving Anthropic and OpenAI are increasing scrutiny of AI containment.
A logo of Meta AI appears on a screen at the World Economic Forum in Davos, Switzerland, in 2025. Photograph: Yves Herman/Reuters
A logo of Meta AI appears on a screen at the World Economic Forum in Davos, Switzerland, in 2025. Photograph: Yves Herman/Reuters
Meta says its AI model hacked into another company during testing
Company is the third to report such an incident after Anthropic and OpenAI reported breaches during training
Reuters
Thu 6 Aug 2026 02.27 BSTLast modified on Thu 6 Aug 2026 02.29 BST
[Share
[Prefer the Guardian on Google
](https://www.google.com/preferences/source?q=theguardian.com)
Meta said on Wednesday that one of its AI models hacked another company during cybersecurity testing, after an error by its testing partner gave the model unintended internet access.
The incident adds to a growing list of cases in which AI agents from major developers breached systems at other companies during testing, after Anthropic said last week that some of its models hacked three companies, and OpenAI disclosed that an AI agent breached the startup Hugging Face.
[
AI models have been going rogue in tests – how worried should we be?
Read more
](https://www.theguardian.com/technology/2026/aug/05/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be)
Meta said a misconfiguration by the independent testing company Irregular inadvertently allowed one of its models internet access during an evaluation, adding that it was investigating the incident.
The model “exploited a security vulnerability in a third-party service, in a manner similar to previously reported instances with other companies”, Meta said in a statement.
Earlier in the day, The Information, citing sources, reported that Meta’s Muse Spark 1.1 model, which it has touted as its most capable model for real-world coding and agentic tasks, breached an unidentified company and altered its internal systems.
A spokesperson for Irregular told Reuters the incident was the “exact same evaluation-environment issue that was already disclosed by Anthropic last week” and that it did not involve a “sandbox escape or a sophisticated cyber action”.
“There are no current open issues. Irregular is developing a white paper to share best practices for containment and securely running cyber evaluations,” Irregular said.
The incidents revealed by Meta and Anthropic were due to mistakes that inadvertently gave their models access to the open internet. That contrasts with OpenAI, whose AI agent independently exploited a novel vulnerability to reach the internet during cyber testing.
skip past newsletter promotion
| Free newsletter | Weekly |
Sign up to TechScape
A weekly dive in to how technology is shaping our lives
Preview latest
Enter your email
Sign up
after newsletter promotion
Even so, the breaches highlight how AI has increased threats to cybersecurity and how developers can struggle to keep the capabilities of their models contained.
The disclosures are likely to intensify a US government push to better manage AI security risks at a time when Anthropic and OpenAI are racing to release more capable systems ahead of their planned public listings. Prominent leaders at these labs have called for a slowdown to address risks first.
Explore more on these topics
[Share