Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍 PyPI
Not in CISA KEV

CVE-2026-42208

CVE-2026-42208 is a SQL Injection vulnerability in litellm. EPSS puts its 30-day exploitation probability at 89.4% (100th percentile). O3 Security confirms whether CVE-2026-42208 is actually reachable in your code before you act, and blocks exploitation at runtime until you patch.

LiteLLM: SQL injection in Proxy API key verification

Also known asGHSA-r75f-5x8p-qvmcPYSEC-2026-391
Published
May 8, 2026
Updated
Aug 12, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Sep 8, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

Actively exploited in the wild

  • CISA’s SSVC triage classifies this CVE as under active exploitation.
  • CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
  • A successful exploit gives an attacker total control of the affected component, not partial access.

Exploitation and automatability from CISA’s SSVC triage for CVE-2026-42208.

EPSS Exploitation Probability

via FIRST.org ↗
89.4%probability of exploitation in next 30 days
Very High Risk0.00%
Lower risk than most CVEs100th percentile — riskier than 100% of all scored CVEsHighest risk
43.7%62.5%81.2%100.0%54.3%84.5%89.4%89.4%89.4%Jun 26Aug 26Sep 26

EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.

Real-World Exposure

1 pkg affected
🐍litellm

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

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.

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIlitellm1.81.16&&< 1.83.71.83.7

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for litellm. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

  2. Fix

    Update litellm to 1.83.7 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-42208 is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 pinpoints whether CVE-2026-42208 is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to CVE-2026-42208. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

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
O3 Security · Impact-Aware SCA

Is CVE-2026-42208 in your dependencies?

O3 detects CVE-2026-42208 across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.

CVE-2026-42208: LiteLLM: SQL injection in… | O3 Security