Raw vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XSummary
CVE-2026-42208 is a critical-severity SQL Injection (CWE-89) vulnerability in Litellm Litellm. Its CVSS base score is 9.3 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked in the top 0.2% of CVEs by exploit likelihood; CISA has added it to the Known Exploited Vulnerabilities catalog.
This vulnerability is AI-related — categorised as APIs and Models; in the Data-Related Vulnerabilities risk domain.
The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
LiteLLM is an AI gateway proxy that routes calls to LLM provider APIs using an OpenAI-compatible interface. CVE-2026-42208 is a SQL injection vulnerability (CWE-89) present in versions 1.81.16 through 1.83.6. During proxy API-key validation, the code interpolated an attacker-supplied value directly into a database query string instead of using a parameterized statement; the flawed query could be reached on any LLM endpoint through the proxy’s error-handling path.
An unauthenticated remote attacker can exploit the flaw by sending a crafted Authorization header to routes such as POST /chat/completions. Successful exploitation allows arbitrary read and write access to the proxy’s database, enabling theft or modification of stored API keys and other credentials and thereby granting unauthorized control of the LiteLLM instance and the downstream LLM providers it manages.
The vulnerability is fixed in release 1.83.7. The project’s GitHub advisory and release notes recommend immediate upgrade; the issue is also listed in CISA’s Known Exploited Vulnerabilities catalog, confirming observed in-the-wild exploitation. The associated EPSS score stands at 0.6259 with no material increase after disclosure.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-28503
Vulnerability Data
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…
more
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.
- CWE(s)
- KEV Date Added
- 08 May 2026
AI Security AnalysisAI
- AI Category
- APIs and Models
- Risk Domain
- Data-Related Vulnerabilities
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai, llm, openai
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V6.2.5
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation can discover SQLi flaws before deployment but does not stop their introduction.
Input validation directly stops untrusted data from reaching SQL query construction without neutralization.
Secure engineering principles require parameterized queries and input sanitization that structurally eliminate SQLi.
System monitoring can identify attempted SQLi exploitation via anomalous queries after the weakness exists.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure SDLC practices directly target injection flaws during coding and review so largely prevent CWE-89 introduction, yet the single broad outcome leaves residual risk from incomplete neutralization techniques or missed edge cases.
Training raises developer awareness of SQLi risks and can reduce introduction likelihood (partial) but removes none of the actual coding flaw's risk by itself since technical neutralization is still required.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
The same secure-coding and static-analysis activities surface missing neutralization of SQL metacharacters before the system is accepted.
Early warnings and shared best-practice information help organizations apply the latest remediation techniques against SQL-injection vulnerabilities.
Threat-intelligence feeds that surface new SQL-injection campaigns enable rapid updates to query-construction defenses and detection signatures before exploitation occurs.
Secure-coding rules and security testing phases mandate the use of parameterized queries or equivalent escaping, preventing the construction of dynamic SQL statements from untrusted input.
Language-specific secure coding rules, peer review and SAST together prevent the construction of SQL statements from untrusted data without proper parameterization or escaping.