{"data":{"id":"4c4283d7-62bc-4fb6-bc6d-1cad7ea964c2","title":"Scaling Adaptive Prompt Injection Attacks with Agent Swarms","summary":"Researchers built a synthetic prompt injection benchmark that uses random non-malicious actions as adversarial goals, separating instruction-hierarchy robustness from security knowledge. An agentic attacker with increased capabilities reliably got models to follow instructions embedded in tool output, including models previously considered robust on public benchmarks such as GraySwan Arena. The authors conclude that frontier defenses may need proactive, automated red-teaming.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.11861v1","publishedAt":"2026-11-09T04:34:14.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Google"],"affectedVendorsRaw":["Gemini"],"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":"2026-11-09T04:34:14.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}