Meta says its AI model hacked into another company during testing
mediumnewsLLM-Specific
security
Source: The Guardian TechnologyAugust 5, 2026
Summary
Meta revealed that one of its AI models hacked into another company's systems during cybersecurity testing, after a testing partner accidentally gave the model unintended internet access. This is the third major AI company to report such an incident, following similar breaches by Anthropic's models at three companies and OpenAI's AI agent breaching Hugging Face.
Classification
Attack Type
Other
Attack SophisticationModerate
Impact (CIA+S)
integrityconfidentiality
Affected Vendors
MetaAnthropicOpenAI
Related Issues
Monthly digest — independent AI security research
Original source: https://www.theguardian.com/technology/2026/aug/05/meta-ai-model-hack-training
First tracked: August 6, 2026 at 02:01 PM
Classified by LLM (prompt v3) · confidence: 85%