Anthropic announced an expanded version of its Cyber Verification Program (CVP), consolidating its earlier Project Glasswing initiative and the original CVP into a single offering. The program grants qualifying security professionals access to advanced cyber capabilities and reduced blocking classifiers, and now offers three access tiers so teams can apply for the level that matches their work.
According to the company, cybersecurity is inherently dual use: the same capabilities that help defenders find and fix vulnerabilities can also be exploited by malicious actors. For that reason, generally available models such as Claude Opus 5.5, Claude Fable 5.1, and Claude Sonnet 5.5 carry conservative cyber safeguards that block most cyber work, while Anthropic works to reduce false positives for secure coding.
The three tiers are structured around the scope of a team's cyber work:
- Defense Access covers defensive tasks such as security operations center and incident response work, reverse-engineering malware, and analyzing and validating vulnerabilities. It is aimed at security teams at companies, nonprofits, universities, and government bodies defending systems they own or maintain, as well as critical infrastructure operators, smaller security firms, open-source maintainers, and individual researchers with a track record of reported vulnerabilities. Anthropic says it aims to respond to applications within a few days.
- Red Team Access adds authorized penetration testing and red-teaming to the defensive uses above, for in-house red teams, government red teams, and security and penetration testing firms. Adversarial testing is limited to systems the organization is authorized to test. Real-time blocks remain on actions that could cause physical harm or mass disruption, such as deploying ransomware, damaging physical systems, or pen testing high-risk safety systems. Review is expected to take a few weeks, and this tier is for organizations only.
- Specialized Access, with the fewest cyber blocks, is reserved for a limited set of verified organizations authorized to test safety systems that could impact lives or disrupt markets, such as flight operating systems, power grids, telecom networks, interbank transfer infrastructure, and government administrative networks. Anthropic says it reviews every organization in this tier in depth in collaboration with the US government, and existing Project Glasswing members transition to it without reapproval for current models.
Anthropic said data retention is required for enrolled organizations so it can monitor for cyber misuse. Once Enterprise Frontier Safeguards (EFS) becomes available later this fall, eligible organizations will be able to store data in cloud infrastructure they control. Until then, organizations with access to Claude Fable 5.1 or Claude Mythos 5.1 with zero data retention can also use CVP with zero data retention.
To assess the efficacy of its protections, Anthropic ran Claude Opus 5.5 through CyScenarioBench, an evaluation measuring whether models can plan and execute multi-stage cyber operations under realistic constraints, with safeguards tuned for each tier. Across five attempts at each of 10 challenges per tier, the company reported that without CVP access every task was blocked on the first prompt; in Defense Access, 46 of 50 trials were blocked at some point while four succeeded; and in Red Team Access, no blocks occurred and the model completed 34 of 50 tasks, effectively equivalent to its 67.6% success rate with no safeguards applied.
Anthropic also reported outcomes from Project Glasswing: partners uncovered at least 129,000 verified software vulnerabilities between April and July 2026, and its own open-source scanning found an additional 5,500 verified vulnerabilities between April and October 2026. More than 33,000 of these were rated critical- or high-severity, a figure Anthropic describes as likely an undercount based on survey data from only a subset of partners. CVP is available on the Claude Platform, Google Cloud's Vertex AI, and Microsoft Foundry, and only on Amazon Bedrock for customers eligible for Enterprise Frontier Safeguards.