{"data":{"id":"16fb8858-fd0c-4298-b1b2-3ea49b81954f","title":"The Goal Tells an Agent What to Do. Security Has to Govern How.","summary":"Check Point describes an approach to governing autonomous AI agents, arguing that a goal does not define permitted methods and that security must control how an agent acts. It pairs NVIDIA's Open Agent Safety Platform, which places the boundary in infrastructure outside the agent's reach, with Check Point semantic monitoring that judges whether each step still fits the task. The two work together in a beta integration with NVIDIA OpenShell, and the monitor's verdict can arrive in under 100 milliseconds, before the action runs.","solution":"N/A -- no mitigation discussed in source.","labels":["security","industry"],"sourceUrl":"https://blog.checkpoint.com/ai-security/check-point-nvidia-openshell/","publishedAt":"2026-09-28T10:40:21.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedVendors":["NVIDIA"],"affectedVendorsRaw":["NVIDIA Open Agent Safety Platform","NVIDIA OpenShell","Check Point semantic monitoring"],"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":"2026-09-28T10:40:21.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":false,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}