CVE-2026-42208: BerriAI LiteLLM SQL Injection Vulnerability
CVE-2026-42208 is a critical-severity flaw (CVSS 9.8) affecting litellm, reported as exploited in the wild. Below: why it ranks where it does, which versions are affected, what to do, and the exact commands.
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 throu
Why this priority
- Critical severity
- EPSS top 1%: very likely to be exploited
- Exploited in the wild (CISA KEV)
- Public exploit reference
- CISA SSVC: automatable with total technical impact
- Remotely exploitable, no login, no user action
A fixed release or distro patch exists.
Risk facts
| CVSS score | 9.8 (Critical) |
| Attack vector | Network (remote) |
| Attack complexity | Low |
| Privileges needed | None |
| User interaction | None |
| EPSS exploit chance | 89.4% (top 1%) |
| CISA exploited list | Yes, fix due 2026-05-11 |
| Weakness | CWE-89 |
| Published | 2026-05-08 |
| Last modified | 2026-10-26 |
Last updated 2026-10-26 · Sources: CVE Program, NVD, CISA KEV, EPSS and vendor advisories · How we score
Am I affected?
Timeline
- Exploited Added to the CISA Known Exploited Vulnerabilities list
- Published CVE record published
- Deadline CISA due date for US federal agencies to patch
- Updated Record last modified
Exact fixes by distribution
Public exploits and detection
Public code exists for this CVE. Treat unpatched systems as at risk, and only run PoCs in a lab.
- GitHub PoC: ridhinva/litellm-sqli-scanner (1 stars)
- GitHub PoC: imjdl/CVE-2026-42208_lab (0 stars)
- GitHub PoC: 0xBlackash/CVE-2026-42208 (0 stars)
- Metasploit: BerriAI LiteLLM Proxy Pre-Auth SQL Injection Scanner
- Nuclei scan template: LiteLLM - SQL Injection
Advisories and coverage
Research and news
- Sysdig Threat Research: CVE-2026-42208: Targeted SQL injection against LiteLLM's authentication path discovered 36 hours following vulnerability disclosure 2026-04-27
Scores and fixes here are computed automatically from those and other public sources. Confirm with the vendor advisory before changing production systems.
Quick answers
How do I fix CVE-2026-42208?
litellm: upgrade to 1.83.7. Exact commands for each OS are on this page.
Is CVE-2026-42208 being exploited?
Yes. CVE-2026-42208 is on the CISA Known Exploited Vulnerabilities list, so treat it as patch-now.
What does CVE-2026-42208 affect?
CVE-2026-42208 affects litellm. Severity is critical (CVSS 9.8). 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 i
How urgent is CVE-2026-42208?
Priority 97/100. Critical severity; EPSS top 1%: very likely to be exploited; Exploited in the wild (CISA KEV); Public exploit reference; CISA SSVC: automatable with total technical impact; Remotely exploitable, no login, no user action
Software pages
OpenAI and LLM tools vulnerabilities
Related CVEs
- CVE-2026-40217 HIGH 8.8 UPGRADE LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /gu
- CVE-2026-42271 HIGH 8.8 EXPLOITED UPGRADE UPGRADE BerriAI LiteLLM Command Injection Vulnerability
- CVE-2026-42203 HIGH 8.8 UPGRADE LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format
- CVE-2026-49468 CRITICAL 9.8 UPGRADE LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format
- CVE-2026-12773 HIGH 7.3 UPGRADE A weakness has been identified in BerriAI litellm up to 1.59.8