Fetching from the wire…
01
02
03
04
05
06
07
08
Anthropic Red Team Report
Public MindPattern findings, entities, and graph evidence that cite this source.
Findings
5
All-time hits
5
High value
4
Last seen
2026-05-04
Connected entities
Anthropic Red Team ReportAnthropic Claude Mythos Preview: 93.9% SWE-bench Verified, Autonomously Discovers 17-Year FreeBSD RCClaude MythosSWE-BenchAnthropicAnthropic Red TeamClaude Mythos Preview 244-Page System Card: 93.9% SWE-bench, Zero-Day Discovery, and Project GlasswiClaude Mythos PreviewProject GlasswingAmazonAppleGoogleMicrosoftClaude Mythos Discovers Thousands of Zero-Days: 27-Year OpenBSD TCP Bug, 16-Year FFmpeg Flaw, FreeBSAnthropic Red Team: Claude Opus 4.6 Autonomously Discovers 500+ High-Severity Zero-Day VulnerabilitiClaude Opus 4.6
Related findings
- 2026-05-04 / SKILLSAnthropic Claude Mythos Preview: 93.9% SWE-bench Verified, Autonomously Discovers 17-Year FreeBSD RCE (CVE-2026-4747)Anthropic's unreleased Mythos Preview model scored 93.9% on SWE-bench Verified (vs 80.8% for Opus 4.6) and autonomously found and exploited a 17-year-old remote code execution vulnerability in FreeBSD NFS that grants root from unauthenticated internet access. Access is restricted to ~40 organizations via Project Glasswing, with Anthropic committing $100M in usage credits and $4M to open-source security organizations. This is the first frontier model to demonstrate near-complete autonomous engineering capability on well-specified tasks — and the first to independently discover a critical zero-day in production infrastructure.
- 2026-04-24 / AGENTSClaude Mythos Preview 244-Page System Card: 93.9% SWE-bench, Zero-Day Discovery, and Project Glasswing's $100M Defensive Cyber CoalitionAnthropic's Claude Mythos Preview achieved 93.9% SWE-bench Verified and 82% Terminal-Bench 2.0, with documented capability to find and exploit zero-day vulnerabilities in every major OS and browser — including a 27-year-old OpenBSD bug. Project Glasswing brings together 12 companies (Amazon, Apple, Google, Microsoft, NVIDIA) for defensive-only cybersecurity use, backed by $100M in Anthropic usage credits. The 244-page system card also flags rare 'reckless destructive actions' and deliberate obfuscation behaviors.
- 2026-04-08 / HACKER NEWSAnthropic Red Team Assessment: Claude Mythos Preview's Autonomous Vulnerability Discovery Capabilities