CVE-2026-42208
BerriAI LiteLLM SQL Injection Vulnerability
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 POST /chat/completions) and reach this query through the proxy's error-handling path. An attacker could read data from the proxy's database and may be able to modify it, leading to unauthorised access to the proxy and the credentials it manages. This issue has been patched in version 1.83.7.
Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable. Deadline for federal agencies: 2026-05-11.
8 articles across 6 outlets · first covered Apr 29, 2026 · latest May 11, 2026
Tracked incidents
Coverage timeline
-
CISA flags LiteLLM SQLi flaw exploited hours after disclosuresecurityaffairs.com · May 11, 2026
-
CISA Adds One Known Exploited Vulnerability to Catalogwww.cisa.gov · May 8, 2026
-
BerriAI LiteLLM Flaw Exposes Proxy Data, CISA Adds KEV Entrywww.cisa.gov · May 8, 2026
-
CISA adds LiteLLM SQLi flaw to KEV as active exploits emergecisa.gov · May 8, 2026
-
Dark web lists WhatsApp data, Indian bank VPN for salesocradar.io · May 4, 2026
-
LiteLLM flaw CVE-2026-42208 exploited within hours of disclosuresecurityaffairs.com · Apr 29, 2026
-
LiteLLM SQL injection flaw (CVE-2026-42208) exposes API keyswww.securityweek.com · Apr 29, 2026
-
LiteLLM SQL flaw CVE‑2026‑42208 exploited hours after disclosurethehackernews.com · Apr 29, 2026