# CVE-2026-108575: BerriAI LiteLLM improper authorization in secret resolution

Source: https://junglewise.ai/threats/cve-2026-108575-a-vulnerability-has-been-found-in-berriai-litellm-up-to-1-94-0  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-10-11. Updated: 2026-10-16  
License: CC BY 4.0 with a link back

CVE-2026-108575 · Severity: medium · CVSS 6.3 · Published 2026-10-11

LiteLLM is a library that manages API keys and secrets for large language model integrations. A flaw in its secret resolution component allows attackers to manipulate the api_key argument and bypass authorization checks remotely. This could enable unauthorized access to API credentials and external services.

Technologies: [Berriai LiteLLM](https://junglewise.ai/threats/technologies/litellm). Vendors: [Berriai](https://junglewise.ai/threats/vendors/berriai).

## Quick answers

**Is CVE-2026-108575 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-108575 being exploited in the wild.

**How severe is CVE-2026-108575?** Medium severity, with a CVSS score of 6.3, published 11 October 2026.

**Which products and versions are affected?** Berriai LiteLLM up to 1.94.0.

**Is there a fix for CVE-2026-108575?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-108575 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-108575?** Check whether you run Berriai LiteLLM at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

The get_secret function in secret_managers/main.py does not properly validate the api_key argument, leading to an improper authorization vulnerability. An attacker can remotely manipulate this argument to bypass authentication controls. The vulnerability affects LiteLLM versions up to 1.94.0, and no patch has been confirmed.

## Affected products

- BerriAI LiteLLM up to 1.94.0

## Timeline

- 2026-10-11: disclosed

## References

- [https://github.com/user-attachments/assets/039cccbf-f4a5-460a-aec2-120049634200](https://github.com/user-attachments/assets/039cccbf-f4a5-460a-aec2-120049634200)
- [https://vuldb.com/cve/CVE-2026-108575](https://vuldb.com/cve/CVE-2026-108575)

## Related threats

- [LiteLLM arbitrary local file read via vertex_ai_credentials](https://junglewise.ai/threats/litellm-internal-user-viewer-arbitrary-local-file-read-via-vertex-ai-649a7475)
- [LiteLLM reflected XSS in SSO debug callback endpoint](https://junglewise.ai/threats/litellm-vulnerable-to-reflected-xss-in-sso-debug-callback-38154651)
- [LiteLLM proxy authentication bypass via reused crypto context](https://junglewise.ai/threats/cve-2026-114612-litellm-is-a-proxy-server-ai-gateway-to-call-llm-apis-in-openai)
- [BerriAI LiteLLM authorization bypass in spend tracking](https://junglewise.ai/threats/cve-2026-108574-a-flaw-has-been-found-in-berriai-litellm-up-to-1-95-0-affected)
- [BerriAI LiteLLM tenant isolation bypass in semantic cache](https://junglewise.ai/threats/cve-2026-89032-berriai-litellm-before-1-101-0-rc-1-contains-a-tenant-isolation)