Unauthenticated database reading and modification via SQL injection
Published May 8, 2026 · Updated May 8, 2026
SQL injection in the LiteLLM proxy 1.81.16 through 1.83.6 allows remote attackers to read or modify its database via an Authorization header. The proxy API key check interpolates the caller-supplied key into SQL instead of passing it as a separate database parameter. No credentials or user interaction are required; any LLM API route reaches the query through the error-handling path, exposing proxy data and managed credentials to unauthorized access or modification.
Summary
What happened
SQL injection in the LiteLLM proxy 1.81.16 through 1.83.6 allows remote attackers to read or modify its database via an Authorization header. The proxy API key check interpolates the caller-supplied key into SQL instead of passing it as a separate database parameter. No credentials or user interaction are required; any LLM API route reaches the query through the error-handling path, exposing proxy data and managed credentials to unauthorized access or modification.
The record
- CVE
- CVE-2026-42208
- Published
- May 8, 2026
- Updated
- May 8, 2026
- Vendor
- Berri AI
- Product
- LiteLLM
- Classifications
- CWE-89, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- May 8, 2026Exploitation reportedCISA Known Exploited Vulnerabilities catalog listing
- May 8, 2026CVE publishedPublication date reported by the CVE source.
- May 8, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=>= 1.81.16, < 1.83.7
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- CVE-2026-42208 LiteLLM timing-based SQL injection proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Reported exploitation
- CISA Known Exploited Vulnerabilities catalog listingknown exploited catalog
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo