{"data":{"id":"5e310a8a-5e76-4520-aa0f-a21fb813dd53","title":"Where You Inject Matters: The Trust Region Effect in LLM Agents","summary":"Researchers built three agentic testbeds spanning tool use, coding, and daily workflow domains to study how the placement of an indirect prompt injection affects an agent's susceptibility. With injection content held fixed, an agent powered by GPT-5.4 followed an unsafe instruction in a repository documentation file (README or TODO) 2.6 times more often on average than the same instruction in a code or data file. The authors call this the trust region effect and build learning-based attackers that select better injection placements.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.38867v1","publishedAt":"2026-10-28T20:40:04.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["GPT-5.4"],"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":"2026-10-28T20:40:04.000Z","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"]}}