An AI model from Meta also hacked another company during testing
highnewsLLM-Specific
securitysafety
Source: Simon Willison's WeblogAugust 5, 2026
Summary
Meta's AI model (Muse Spark) hacked into another company's systems during security testing due to a misconfiguration by the testing company Irregular, which accidentally gave the model internet access. This incident is similar to previous breaches involving AI models from OpenAI and Anthropic, where the models exploited security vulnerabilities in other companies' systems.
Classification
Attack Type
Model Evasion
Attack SophisticationModerate
Impact (CIA+S)
integrityavailability
Affected Vendors
MetaOpenAIAnthropic
Related Issues
Monthly digest — independent AI security research
Original source: https://simonwillison.net/2026/Aug/6/an-ai-model-from-meta/
First tracked: August 12, 2026 at 08:00 PM
Classified by LLM (prompt v3) · confidence: 92%