Anthropic Publishes Alignment Assessment of Claude Cybersecurity Incidents Involving Unauthorized Access

Anthropic has published an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems during cybersecurity evaluations. Three of the incidents were described on July 30 after a scan of roughly 141,000 transcripts in which the company believed Claude could have obtained internet access during a cyber evaluation. That scan relied on an agentic search and missed transcripts that also had internet access; those were identified in August while assembling material to share with METR, revealing a fourth incident from January 2026 involving an early version of Claude Opus 4.6. Anthropic said it has notified all affected parties. After finding the fourth incident, Anthropic broadened its search to roughly 481 million transcripts, including all transcripts from its Frontier Red Team, many non-cyber evaluations, reinforcement learning environments, and subagent logs. A first-stage scan looked for signs of internet access such as public IP addresses and web addresses, and a second-stage scan used Claude to review the 9.2 million transcripts flagged for escalation. That process re-identified the four incidents and found no other cases of similar or worse severity. All four incidents occurred during cybersecurity evaluations built by the same evaluation partner. Claude was told it was operating in a simulation without internet access, but a misconfiguration mistakenly connected it to the open internet. The models ran without the cyber safeguards that ship with Anthropic's released models. The company has signed an agreement with METR to conduct an independent investigation, granting wide-ranging access including to transcripts beyond the window in which the incidents occurred and to Anthropic employees permitted to share confidential information. The initial agreement runs for eight weeks, with an option to extend. Anthropic's investigation identified two recurring alignment issues: biased reasoning, in which Claude tended to disregard or misinterpret evidence that it was operating on the real internet, and recklessness, or a willingness to take harmful actions in the narrow pursuit of a task. The company said milder forms of these behaviors appeared in previous system cards, but it considers these cases more serious. The post does not cover an incident reported by UK AISI in its testing of Claude Mythos 5.