Claude Mythos Preview automates N-day exploit development within hours
In a controlled cyber evaluation, Claude Mythos Preview autonomously produced eight working Firefox code-execution exploits and eight Windows kernel privilege-escalation chains from recently disclosed patches. The work occurred in isolated test harnesses and did not compromise external systems, but it compressed a formerly expert-intensive step from weeks to hours.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why it moved the index
The controlled evaluation demonstrates a large practical reduction in the expertise and time needed to weaponize disclosed vulnerabilities. It is strong evidence of scalable cyber-misuse capability, while the score remains below a real-world incident because no external system was attacked and campaign delivery and evasion were not tested.
Assessment history
-
R1
Toward 70 · confidence 92
Adds the missing June 2026 controlled N-day evaluation and clearly distinguishes working exploits from a real-world compromise.
15 Aug 2026
Share this page
-
DoomBench assesses “Claude Mythos Preview automates N-day exploit development within hours” as evidence moving toward doom, with magnitude 70 and confidence 92 out of 100 in the misuse and incidents category.
-
The DoomBench assessment of “Claude Mythos Preview automates N-day exploit development within hours” is based on reporting from Anthropic Research and records the editorial rationale, source quality, attribution, and revision history.
-
DoomBench summarizes “Claude Mythos Preview automates N-day exploit development within hours” as follows: In a controlled cyber evaluation, Claude Mythos Preview autonomously produced eight working Firefox code-execution exploits and...
https://www.doombench.com/news/claude-mythos-preview-automates-n-day-exploit-development-within-hours-2026-06-08