Skip to content
Security Flaws in LLM Lead to API Key Leakage

Security Flaws in LLM Lead to API Key Leakage

First seen 12 Nov 2026, 03:42 UTC • •

Article Content

Browse articles
ThreatCluster AI
ThreatCluster •November 12, 2026 at 03:43 UTC
  • •Two critical vulnerabilities in LLM could leak OpenAI API keys.
  • •Affected versions range from 0.32a2 to 0.37.1; fixed in 0.37.2.
  • •Users must upgrade to the latest version to prevent API key exposure.

Two security vulnerabilities (GHSA-v9h7-jj4g-f862 and GHSA-r639-rr7r-x72w) were discovered in the LLM software, affecting versions 0.32a2 through 0.37.1. These flaws could unintentionally expose users' OpenAI API keys to third-party providers when using custom models with specific configurations. The vulnerabilities arise when the api_key_name is not set or when a stored key is not available, leading to the fallback on the OPENAI_API_KEY environment variable. The issues were reported by Daniel de Araujo and have been addressed in the recent release of version 0.37.2. Users are urged to upgrade immediately to mitigate the risk of key leakage. The vulnerabilities affect a wide range of users employing LLM for various applications.

Start a free Starter trial for enhanced analysis

Ask AI about this cluster

Timeline

2026-11-11
LLM version 0.37.2 released
Version 0.37.2 was released to fix critical vulnerabilities that could leak OpenAI API keys.
Simon Willison
2026-11-12
Advisories GHSA-v9h7-jj4g-f862 and GHSA-r639-rr7r-x72w published
GitHub published advisories detailing the vulnerabilities affecting LLM versions 0.32a2 through 0.37.1.
github.com

More articles in this cluster (3)

Following this threat?

Track OpenAI in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.

Free account · no card needed

Common questions

Which versions are affected?
LLM versions from 0.32a2 through 0.37.1 are affected by these vulnerabilities.
What should I do if I'm using an affected version?
Upgrade to LLM version 0.37.2 immediately to mitigate the risk of API key leakage.
Are these vulnerabilities being actively exploited?
No active exploitation has been reported; however, the vulnerabilities could lead to key leakage if not patched.