Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
CISA KEV·Added 2026-05-08 — agencies required to remediate by 2026-05-11
🐍 PyPI

GHSA-r75f-5x8p-qvmc

CRITICAL

LiteLLM has SQL Injection in Proxy API key verification

Also known asCVE-2026-42208PYSEC-2026-391
Published
Apr 24, 2026
Updated
Jun 29, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed

EPSS Exploitation Probability

via FIRST.org ↗
87.3%probability of exploitation in next 30 days
Very High Risk100th percentile+2.78%
44.4%62.0%79.6%97.2%54.3%84.5%87.3%Jun 26Jul 26Jul 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.

Blast Radius

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

Impact

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.

Patches

Fixed in 1.83.7. The caller-supplied value is now always passed to the database as a separate parameter. Upgrade to 1.83.7 or later.

Workarounds

If upgrading is not immediately possible, set disable_error_logs: true under general_settings. This removes the path through which unauthenticated input reaches the vulnerable query.

References

Discovery Credit: Tencent YunDing Security Lab

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 GHSA-r75f-5x8p-qvmc 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 GHSA-r75f-5x8p-qvmc 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 GHSA-r75f-5x8p-qvmc. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

### Impact 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. ### Patches Fixed in **`1.83.7`**. The caller-supplied value is now
O3 Security · Impact-Aware SCA

Is GHSA-r75f-5x8p-qvmc in your dependencies?

O3 detects GHSA-r75f-5x8p-qvmc across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.