{"data":{"id":"d482e0c3-8658-436d-bd78-6931a13e887e","title":"AgentForger proves AI agents can become persistent insider threats","summary":"AgentForger is a phishing-based attack that tricks users into creating a rogue AI agent within OpenAI workspaces, giving attackers a persistent insider threat (an automated tool that stays active and follows attacker commands indefinitely). Once activated with a single click, the agent gains full access to apps like Outlook, Slack, and Google Drive, can approve its own actions without asking users, and receives new tasks from attacker-controlled email addresses to steal data, harvest credentials, and launch phishing campaigns.","solution":"OpenAI resolved the vulnerability four days after disclosure.","labels":["security","safety"],"sourceUrl":"https://www.csoonline.com/article/4200978/agentforger-proves-ai-agents-can-become-persistent-insider-threats.html","publishedAt":"2026-07-24T00:29:34.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"high","attackType":["prompt_injection","supply_chain"],"issueType":"news","affectedPackages":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["OpenAI","ChatGPT","Workspace Agents","Outlook","Slack","SharePoint","Google Drive","Gmail","Teams"],"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":"2026-07-24T00:29:34.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["confidentiality","integrity","availability"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}