{"version":1,"type":"story","url":"https://digestai.news/story/delinea-tests-anthropic-claude-mythos-5-1-on-its-own-privilegedaccess","json":"https://digestai.news/story/delinea-tests-anthropic-claude-mythos-5-1-on-its-own-privilegedaccess.json","markdown":"https://digestai.news/story/delinea-tests-anthropic-claude-mythos-5-1-on-its-own-privilegedaccess.md","slug":"delinea-tests-anthropic-claude-mythos-5-1-on-its-own-privilegedaccess","headline":"Delinea tests Anthropic Claude Mythos 5.1 on its own privileged‑access code","summary":"Delinea, an identity‑security company, has joined Anthropic’s Project Glasswing to run the Claude Mythos 5.1 model against parts of its own software that store, broker, and rotate privileged credentials. The experiment turns the frontier AI model inward, letting it scan vaulting logic, secret storage, rotation mechanisms, key management, session‑brokering code, and policy‑enforcement paths for weaknesses that could affect privileged access.\n\nCEO Art Gilliland said the goal is to use the best tools available to attack the company’s own assumptions and find problems before attackers do. Chief Information Security Officer Pierre Mouallem explained that Mythos is treated like any other privileged identity: its access is scoped, temporary, logged, and runs in an isolated environment with no customer data. Findings will feed into Delinea’s existing security process and be incorporated into secure‑coding standards, pre‑merge checks, and test coverage, aiming to reduce recurring weaknesses in future releases.","keyPoints":["Delinea joined Anthropic’s Project Glasswing to test Claude Mythos 5.1 on its own identity‑security code.","Mythos will examine vaulting, secret rotation, key management, session brokering, and policy enforcement logic.","Delinea treats the model as a privileged identity with scoped, temporary, logged access in an isolated environment."],"whyItMatters":"Using a frontier AI model to audit its own security code shows how AI can become both a testing tool and a privileged identity, reshaping vulnerability discovery for the industry.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Delinea","Anthropic"],"models":["Claude Mythos 5.1"],"people":["Art Gilliland","Pierre Mouallem"]},"firstPublishedAt":"2026-09-22T21:05:00Z","updatedAt":"2026-09-22T21:05:00Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"dqindia.com","title":"Delinea tests Anthropic AI against its own security code","url":"https://dqindia.com/data-and-ai/delinea-tests-anthropic-ai-against-its-own-security-code-12565578","publishedAt":"2026-09-22T21:05:00Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Delinea tests Anthropic Claude Mythos 5.1 on its own privileged‑access code\", 22 September 2026, https://digestai.news/story/delinea-tests-anthropic-claude-mythos-5-1-on-its-own-privilegedaccess","publisher":"Digest AI","title":"Delinea tests Anthropic Claude Mythos 5.1 on its own privileged‑access code","datePublished":"2026-09-22T21:05:00Z","url":"https://digestai.news/story/delinea-tests-anthropic-claude-mythos-5-1-on-its-own-privilegedaccess"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}