{"data":{"id":"8ca78785-2efa-47d5-bad8-76183c3941b5","title":"LLM Heist: Hijacking LiteLLM for Traffic Interception, Key Theft, and Tool-Call Injection","summary":"LiteLLM is an AI gateway (a proxy that provides unified access to multiple LLM providers while keeping API keys secure on the server side) that has become a high-value target for attackers. An attacker who gains the master admin credential can redirect traffic through a malicious gateway to steal API keys, intercept data, forge responses, or inject unauthorized tool calls, all while evading detection. The research describes attack techniques that red teams can use to test these vulnerabilities, noting that unpatched instances and exposed credentials are the primary entry points for this type of compromise.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://embracethered.com/blog/posts/2026/hijacking-litellm-for-fun-and-profit/","publishedAt":"2026-08-03T16:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"high","attackType":["supply_chain","data_extraction","model_theft"],"issueType":"news","affectedPackages":null,"affectedVendors":["LangChain"],"affectedVendorsRaw":["LiteLLM","OpenAI","Anthropic","Azure OpenAI","Bedrock"],"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":"2026-08-03T16:00:00.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality","integrity"],"aiComponentTargeted":"api","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}