# CVE-2026-108574: BerriAI LiteLLM authorization bypass in spend tracking

Source: https://junglewise.ai/threats/cve-2026-108574-a-flaw-has-been-found-in-berriai-litellm-up-to-1-95-0-affected  
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-2026-108574 · Severity: medium · CVSS 4.3 · Published 2026-10-11

BerriAI LiteLLM is an AI gateway that routes requests to multiple language model providers and tracks API costs. An authorization bypass flaw in the spend tracking UI allows an attacker to view other users' spend logs by manipulating the session_id parameter, potentially exposing cost data and usage patterns of other accounts.

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

## Quick answers

**Is CVE-2026-108574 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-108574 being exploited in the wild.

**How severe is CVE-2026-108574?** Medium severity, with a CVSS score of 4.3, published 11 October 2026.

**Which products and versions are affected?** Berriai LiteLLM up to 1.95.0.

**Is there a fix for CVE-2026-108574?** Yes: fixed in 1.96.0. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-108574 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-108574?** 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.

## How to fix

- Fixed in 1.96.0

## Technical details

The vulnerability exists in the ui_view_session_spend_logs function of litellm/proxy/spend_tracking/spend_management_endpoints.py, where insufficient input validation on the session_id parameter allows authorization bypass. An attacker can remotely exploit this via network requests to view spend logs belonging to other sessions without proper authorization checks.

## Affected products

- BerriAI LiteLLM up to 1.95.0

## Timeline

- 2026-10-11: disclosed

## References

- [https://github.com/BerriAI/litellm/](https://github.com/BerriAI/litellm/)
- [https://github.com/BerriAI/litellm/commit/722d9ffa4f6c5ae15702ab9ab2c5f6bf1688308b](https://github.com/BerriAI/litellm/commit/722d9ffa4f6c5ae15702ab9ab2c5f6bf1688308b)

## 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 improper authorization in secret resolution](https://junglewise.ai/threats/cve-2026-108575-a-vulnerability-has-been-found-in-berriai-litellm-up-to-1-94-0)
- [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)