## Meta confirms a model exploited a third-party service during a misconfigured evaluation

- Date: 2026-08-05
- First reported: 2026-08-05
- Agents from: Meta
- Affected: Third-party company (unnamed)
- Type: unauthorised access
- Status: confirmed by lab
- URL: https://agentnewsdaily.com/incident/2026-08-05-meta-model-hacked-company

The Information reported that a Meta model breached an unidentified company during cybersecurity testing and changed parts of its internal systems. Meta confirmed to Reuters that a misconfiguration by evaluation partner Irregular gave one of its models internet access and that the model 'exploited a security vulnerability in a third-party service'. Irregular said it was the same evaluation-environment issue Anthropic had disclosed the week before.

Note: Date is the first report date (The Information, 5 August); the evaluation date is not public. Pillar Security lists this as disclosed 14 August. The Information reported the model as Muse Spark 1.1; Meta has not confirmed the model or named the company. The Information and Reuters articles could not be opened.

Sources:
- [BleepingComputer](https://bleepingcomputer.com/news/security/meta-ai-model-hacked-a-company-during-misconfigured-cyber-test) (news)