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.
Who exploits it and how urgent it is
A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.
How the score was calculated
- Confirmed exploitation (CISA KEV)+35
- Public exploit/PoC (nuclei, metasploit, github)+20
- EPSS 5.8% (30-day exploitation probability)+14
- Technical severity (critical)+10
- Automatable exploitation (SSVC)+3
The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).
Triage
Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.
CISA SSVC assessment CISA
Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.
Remediation
Fixes and mitigations documented by the sources — linked to the original advisory.
- Documented patch — github.com (NIST National Vulnerability Database)
- Documented mitigation — bugzilla.redhat.com (NIST National Vulnerability Database)
- Pip Litellm: fixed in version 1.83.7 — github.com (GitHub Security Advisories)
CISA required action CISA
Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
US federal deadline: May 11, 2026 — passed 157 day(s) ago
First 24 hours
Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.
- Identify exposed assets running the affected vendor/product/version combinations (BerriAI Litellm, Litellm Litellm, Pip Litellm).
- Treat as emergency remediation: the CVE is in CISA KEV (confirmed exploitation).
- The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
- Apply the fixed version or the patch documented under Remediation.
- EPSS ahead of 93% of scored CVEs: prioritize it in the patch queue.
- Search available logs for exploit probes matching the vulnerability class (injection), errors and authentication anomalies.
Affected scope
Vendor, product and versions as the sources word them.
Attack characteristics
The CVSS vector, decoded. It describes the attack, not your exposure to it.
Every base score collected
Sources score independently and may disagree; each row says who scored it and under which version.
| Score | Version | Severity | Expl. | Impact | Scored by |
|---|---|---|---|---|---|
| 9.3 | CVSS 4.0 | Critical | — | — | security-advisories@github.com via NIST National Vulnerability Database |
| 9.3 | CVSS 4.0 | Critical | — | — | GitHub_M via CVE Program (cve.org) e CISA ADP |
| 9.8 | CVSS 3.1 | Critical | 3.9 | 5.9 | nvd@nist.gov via NIST National Vulnerability Database |
| 9.8 | CVSS 3.1 | Critical | 3.9 | 5.9 | 0b0ca135-0b70-47e7-9f44-1890c2a1c46c via NIST National Vulnerability Database |
| 9.8 | CVSS 3.1 | Critical | — | — | GitHub, Inc. via GitHub Security Advisories |
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H (score shown at the top: nvd@nist.gov) Weakness MITRE
Weakness class according to MITRE’s CWE catalog.
CISA KEV details CISA
CISA lists a CVE once it has evidence of exploitation against real targets.
CISA records ransomware use only for campaigns it has confirmed, so “Unknown” means unrecorded, not ruled out. The deadline binds US federal agencies; for everyone else it is a reference date.
Public exploits, PoCs and detection templates
Public code that demonstrates or tests the flaw raises the odds of mass exploitation — and Nuclei templates help find vulnerable assets in your environment.
- BerriAI LiteLLM Proxy Pre-Auth SQL Injection Scanner normal Apr 20, 2026
- Scanner: CVE-2026-42208 LiteLLM SQL Injection — Python scanner for BerriAI LiteLLM proxy instances ★ 1 May 22, 2026
- CVE-2026-42208 lab ★ 0 Apr 28, 2026
- CVE-2026-40487 ★ 0 May 3, 2026
- Threat intelligence brief on CVE-2026-42208, a critical pre-auth SQL injection in BerriAI LiteLLM exploited within 36 hours of disclosure. Covers attack path, detection opportunities, and recommended actions. ★ 0 May 10, 2026
- rootdirective-sec/CVE-2026-42208-Lab ★ 0 May 10, 2026
- HAERIN-L/poc_cve-2026-42208 ★ 0 May 30, 2026
Warning: public PoCs are sometimes disguised malware. Use them only for authorized testing in an isolated environment. This portal does not host exploit code — it only points to the sources.
EPSS over time FIRST
Oct 12, 2026 → Oct 14, 2026 · 3 reading(s) · max 5.77%
Detection
Read off the CVSS vector and the weakness class. Starting points, not tested rules.
- Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
- Look for parameters with command/query metacharacters and unexpected child processes of the service.
- Hunt retroactively in logs from before May 8, 2026 (KEV listing): exploitation may have started earlier.
Timeline
What happened to this CVE, newest first.
- 2026
- Fix documented
- Affected products added · pip/litellm
- Fix documented
- Affected products added · litellm/litellm
- CVSS changed · 9.3 → 9.8
- Source status changed · Published → Analyzed
- Record published
- Affected products added · berriai/litellm
- CVSS changed · 9.3
- Source status changed · → Published
- SSVC assessment updated
- Added to CISA KEV (detected)
- Record created in this database
- CVE published
- Added to CISA KEV catalog
Source activity
Repeated readings are counted rather than listed.
- 3× References added · Oct 13, 2026 – Oct 13, 2026
- 1× Official description updated · Oct 13, 2026 – Oct 13, 2026
References
11 on the record
- github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc
- bugzilla.redhat.com/show_bug.cgi
- www.cisa.gov/known-exploited-vulnerabilities-catalog
- github.com/pypa/advisory-database/tree/main/vulns/litellm/PYSEC-2026-391.yaml
- security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-42208.json
- github.com/advisories/GHSA-r75f-5x8p-qvmc
- github.com/BerriAI/litellm/releases/tag/v1.83.7-stable
- access.redhat.com/security/cve/CVE-2026-42208
- nvd.nist.gov/vuln/detail/CVE-2026-42208
- pypi.org/project/litellm
- github.com/BerriAI/litellm
Elsewhere on this site
Related CVEs (same products)
- Medium CVE-2026-108575 BerriAI LiteLLM Secret Resolution main.py get_secret improper authorization 4d
- Medium CVE-2026-108574 BerriAI LiteLLM Spend Tracking spend_management_endpoints.py ui_view_session_spend_logs authorization 4d
- High CVE-2026-59822 BerriAI LiteLLM Improper Authentication Vulnerability KEV Jul 8, 2026
- Medium CVE-2026-59819 LiteLLM: Local file read via request-supplied OIDC file references Jul 8, 2026
- Medium CVE-2026-59820 LiteLLM: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') Jul 8, 2026
- High CVE-2026-59821 LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks Jul 8, 2026
Not in any source we poll
Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.
- No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
- No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
- No exploit packet captures, log samples, or incident case IDs supplied.
Answered from this record
Text assembled only from the fields above — no additional claims.
What should defenders know first?
CVE-2026-42208 is "BerriAI LiteLLM SQL Injection Vulnerability", rated Critical. It affects Litellm (BerriAI); versions are in the scope table. It is in CISA KEV: there is evidence of real-world exploitation. CVSS 9.8 describes technical severity. EPSS 5.77% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.
Comments
Moderated technical discussion. Read the community guidelines.
No comments yet.
Sign in or create an account to comment and suggest corrections.