{"data":{"id":"b6da83cd-715d-4156-b33e-048c1c08a3c6","title":"Introducing computer use in Gemini 3.5 Flash","summary":"Google has added computer use, a capability that allows AI agents to see and interact with computer screens to perform tasks, directly into Gemini 3.5 Flash (an AI model). This feature enables developers to build agents that can automate work across browsers, phones, and desktops, such as testing software or handling business tasks.","solution":"To mitigate prompt injection risks (attacks where malicious instructions are hidden in user inputs), Google uses targeted adversarial training for computer use in Gemini 3.5 Flash. The company also released two optional enterprise safeguard systems: one that requires explicit user confirmation for sensitive or irreversible actions, and another that automatically stops tasks if an indirect prompt injection is identified. The source recommends combining these features with secure sandboxing, human-in-the-loop verification (having humans review AI decisions), and strict access controls.","labels":["safety","security"],"sourceUrl":"https://deepmind.google/blog/introducing-computer-use-in-gemini-3-5-flash/","publishedAt":"2026-06-24T16:30:01.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"news","affectedPackages":null,"affectedVendors":["Google"],"affectedVendorsRaw":["Google DeepMind","Gemini 3.5 Flash","Gemini 2.5"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-06-24T16:30:01.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}