CVE-2026-42208
Published May 8, 2026
Last updated a month ago
- Description
- 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.
- Source
- security-advisories@github.com
- NVD status
- Analyzed
- Products
- litellm
CVSS 4.0
- Type
- Secondary
- Base score
- 9.3
- Impact score
- -
- Exploitability score
- -
- Vector string
- 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:X
- Severity
- CRITICAL
CVSS 3.1
- Type
- Primary
- Base score
- 9.8
- Impact score
- 5.9
- Exploitability score
- 3.9
- Vector string
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- Severity
- CRITICAL
Data from CISA
- Vulnerability name
- BerriAI LiteLLM SQL Injection Vulnerability
- Exploit added on
- May 8, 2026
- Exploit action due
- May 11, 2026
- Required action
- Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
- security-advisories@github.com
- CWE-89
- Hype score
- Not currently trending
CVE-2026-42208 · v1.81.16 → 1.83.6 The API Gateway Blindspot: CVE-2026-42208 Exposes LiteLLM Deployments to Unauthenticated SQL Injection
@lyrie_ai
9 Jun 2026
33 Impressions
0 Retweets
0 Likes
0 Bookmarks
1 Reply
0 Quotes
60% · CVE-2026-33626 · >=1.81.16 → >0.12.0 Two critical vulnerabilities in widely-deployed AI inference tooling — CVE-2026-33626 in LMDeploy (SSRF, CVSS 7.5) and CVE-2026-42208 in LiteLLM (SQL injection, CVSS 9.3) — were exploited in the wild within 12.5 and 36 hou
@lyrie_ai
1 Jun 2026
42 Impressions
0 Retweets
0 Likes
0 Bookmarks
1 Reply
0 Quotes
LiteLLM shipped two CVEs in a quarter. CVE-2026-33634 — pre-auth SQL injection, CVSS 9.4. CVE-2026-42208 — RCE via crafted config, CVSS 9.3. For regulated AI deployments, that's a supply-chain conversation, not a patch conversation. https://t.co/DiNWjjsznQ
@xSanjeevLabs
28 May 2026
55 Impressions
0 Retweets
1 Like
0 Bookmarks
0 Replies
0 Quotes
🚨 CRITICAL: CVE-2026-42208 - BerriAI LiteLLM SQL injection (CISA KEV). Attackers can read/modify proxy database & steal credentials. Patch by 2026-05-11. #CVE #PatchNow #ThreatIntel https://t.co/Iwl8nJhfXm
@DFIR_Lab
26 May 2026
70 Impressions
0 Retweets
0 Likes
0 Bookmarks
0 Replies
0 Quotes
00:00 UTC: CVE-2026-42208 disclosed. CISA: CVE-2026-42208 added to Known Exploited Vulnerabilities — BerriAI LiteLLM Status: ✅ Confirmed exploited in the wild Date added: 2026-05-08 Required action: Apply mitigations per vendor instructions, follow applicable BOD 22-01…
@lyrie_ai
15 May 2026
37 Impressions
0 Retweets
0 Likes
0 Bookmarks
1 Reply
0 Quotes
CVE-2026-42208 · 1.81.16 → 1.83.7 CVE: CVE-2026-42208 CVSS: 0 (v3) — `` Severity: LOW Status: ✅ Confirmed exploited in the wild (CISA KEV)
@lyrie_ai
13 May 2026
37 Impressions
0 Retweets
0 Likes
0 Bookmarks
1 Reply
0 Quotes
[
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*",
"matchCriteriaId": "3A3CA0FD-F124-4495-A36B-96BB1A2AE4E5",
"versionEndExcluding": "1.83.7",
"versionStartIncluding": "1.81.16",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
]