Anthropic gives more security teams access to Claude with fewer safety restrictions
129,000 vulnerabilities found. Anthropic just expanded its security researcher program — giving more teams jailbreak-adjacent access to Claude for pen testing and malware analysis.
Why it matters
Anthropic is systematically loosening safety guardrails for a growing cohort of security professionals, trading model restriction for vulnerability discovery at scale. Practitioners using Claude in regulated or security-sensitive contexts need to understand the access tiers and their implications.
The key facts
6 to knowCyber Verification Program expanded to more security partners
129,000 confirmed vulnerabilities found April–July 2026 by predecessor program
33,000+ vulnerabilities rated high-severity or critical
Reduced safety restrictions for penetration testing, malware analysis, vulnerability research
Three-tier program structure (implied by 'expansion')
Partner-sourced discovery model
Go to the source
The Decoderthe-decoder.com
Publisher excerpt: Anthropic is expanding its Cyber Verification Program, giving more security professionals access to Claude models with fewer safety restrictions for penetration testing, malware analysis, and vulnerability research. Anthropic says partners in its predecessor program found at least 129,000 confirmed…