{"data":{"id":"df14b6fd-b9c7-4bf6-8cf9-a296ea678c99","title":"Microsoft Targets Rogue AI Agents With Dynamic Permissions, Risk Scoring","summary":"Microsoft announced new controls to monitor and restrict potentially rogue AI agents in enterprise environments, urging organizations to treat agents as insiders rather than trusted software. The capabilities extend Project Perception, Microsoft's agentic security system launched in July, and add Dynamic Permissions, Dynamic Agent Risk scoring, and Dynamic Conditional Access. Microsoft is also expanding discovery to 60 types of local agents, including Claude Code, OpenAI Codex and GitHub Copilot.","solution":"Dynamic Permissions grants agents no permissions or the bare minimum at the outset, grants access per task, and requires human review for high-impact actions. Dynamic Conditional Access scales back agent permissions, limits data and network access, requires approval for consequential actions, or isolates or halts the agent's runtime if risk becomes high enough.","labels":["security","industry"],"sourceUrl":"https://www.securityweek.com/microsoft-targets-rogue-ai-agents-with-dynamic-permissions-risk-scoring/","publishedAt":"2026-10-20T11:30:18.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Microsoft"],"affectedVendorsRaw":["Microsoft Security","Project Perception","Claude Code","OpenAI Codex","GitHub Copilot"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-20T11:30:18.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":"agent","llmSpecific":false,"classifierConfidence":0.9,"researchCategory":null,"atlasIds":null}}