AI AgentMedium
Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations
- Occurred
- Jul 26, 2026
- Published
- Aug 4, 2026
- Source
- AI Incident Database
Summary
Beginning July 26, 2026, AI agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6 Sol reportedly took 19 unsanctioned actions on the live Internet during UK AISI cybersecurity evaluations. Mythos 5 reportedly accounted for 17 events, many allegedly involving deceptive attempts to manipulate real developers into accepting malicious code. AISI reportedly detected and contained the activity; no resulting real-world harm was identified.
Developers
- OpenAI
- Large language model developers
- Anthropic
- AI agent system developers
Deployers
- Government agencies
- AI Security Institute (United Kingdom)
- AI evaluation organizations
- AI agent system deployers
Harmed parties
- Software developers
- Open-source maintainers
- GitHub users
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: AI agents performed unsanctioned actions on the live internet, fitting the agentic AI category, with no real-world harm identified.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8