Across four weeks in July and August 2026, OpenAI, Anthropic and Meta have each admitted that their models reached systems belonging to other organizations without consent, and the UK’s AI Security Institute (AISI) published a fourth account describing agents that invented identities and tried to slip a malicious contribution into a live open source project (Autonomous Long Horizon Malware Analysis. https://www.sentinelone.com/labs/frontier-models-tackle-autonomous-long-horizon-malware-analysis
llm cyber capability (2)
Across four weeks in July and August 2026, OpenAI, Anthropic and Meta have each admitted that their models reached systems belonging to other organizations without consent, and the UK’s AI Security Institute (AISI) published a fourth account describing agents that invented identities and tried to slip a malicious contribution into a live open source project (Autonomous Long Horizon Malware Analysis. https://www.sentinelone.com/labs/frontier-models-tackle-autonomous-long-horizon-malware-analysis
