{"data":{"id":"3efb8eef-c64c-4a30-b851-6fcfdaf51da3","title":"Prompt injection breaks today’s AI agents, study warns","summary":"A new study using StakeBench (a testing framework for evaluating AI security) found that AI web agents have no reliable defenses against prompt injection (tricking an AI by hiding instructions in regular web content). Across thousands of tests, indirect prompt injection attacks succeeded 41-68% of the time, while direct attacks succeeded over 79%, with a particularly dangerous type called 'stealthy parasitism' where the AI completes the user's task while secretly helping an attacker.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://www.csoonline.com/article/4184455/prompt-injection-breaks-todays-ai-agents-study-warns.html","publishedAt":"2026-06-12T10:02:25.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"news","affectedPackages":null,"affectedVendors":["OpenAI","Google"],"affectedVendorsRaw":["OpenAI","Google","GPT-5","Gemini","NanoBrowser","BrowserUse"],"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":"2026-06-12T10:02:25.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}