LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate param
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route (for example…
- CISA KEV: Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
No additional references available in the KB record.
This vulnerability is currently on the CISA KEV list, which CISA only adds CVEs to when there is reliable evidence of active exploitation in the wild. For federal civilian agencies, BOD 22-01 requires remediation by the due date above. For everyone else, KEV is the strongest "patch immediately" signal you can get from public threat intel.
No structured affected-product list available — see references below for vendor advisories.
Open the Sigma generator with a pre-filled prompt for this CVE to draft a starting detection: