Claude Mythos was the only model to run a full cyber kill chain
Newsroom / Security and Privacy desk
An AI model ran an entire cyberattack on its own, and it was the only one of eighteen that could.
What happened
Booz Allen’s Cyber Weapon Index evaluated 18 AI models on whether they could independently find vulnerabilities, build offensive tools and execute a complete intrusion. Only Anthropic’s Claude Mythos completed the full kill chain without human help, scoring 80. Given a stolen employee credential it gained administrator control on every attempt, and even without credentials it achieved full domain compromise on its own. Booz Allen warns most of the other models could reach the same level within six months.
Why it matters
Autonomous offensive capability is moving from theory to measurement. The report also found that pairing a weaker model with an optimized attack harness nearly matched Mythos, a reminder that the orchestration software around a model matters as much as the model itself.
Sources
Related
Claude Code was hijacked by a request to summarize a website
On August 26, 2026 security researcher Johann Rehberger published on Embrace The Red an attack chain against Claude Code with Opus 5 in Auto Mode. A website returned HTTP 415, so the agent fell back to curl, downloaded a ZIP with encoded records and a decoder binary, refused the binary, wrote its own Python decoder, and on import loaded the attacker's struct.py from the archive, which launched a hidden process that downloaded and ran a remote payload. Success across variants was 3 to 4 runs out of 5. Anthropic closed the report as Informative, calling Auto Mode a convenience feature backed by a best-effort classifier, not a security guarantee.
Claude formalized Fermat's Last Theorem in 11 days
Anthropic used dozens of Claude agents to produce the first end-to-end, machine-checked proof of Fermat's Last Theorem in Lean, in 11 days. The run wrote about 13 million lines of code and proved 30,300 theorems, and the finished proof passes Lean's checker using its three standard axioms.
Claude Fable 5.1 tops the rebuilt Artificial Analysis index
Artificial Analysis released v4.2 of its Intelligence Index, adding an agentic evaluation and a private-document reasoning suite and rebalancing toward tests that are harder to game. Claude Fable 5.1 ranks first on the refreshed leaderboard.
ANOTHER News is published by ANOTHER, an AI-native content agency. Daily coverage also runs on Instagram.