Disclosed weakness · no CVE recorded
LiteLLM health errors could disclose internal stack traces
LiteLLM · LiteLLM Proxy · health checks
First documented disclosure · Review checkpoint
Summary
Health-check errors could reveal internal paths and call sites.
Severity and exploitation evidence
No CVSS score recorded in this review.
Exploitation not established: The reviewed sources describe a correction or controlled reproduction; malicious exploitation against users is not established.
Technical severity is not a measure of observed attacks or of risk to your deployment. Attempts, demonstrations, and successful compromise retain the qualifications in the source.
How the weakness works
The response appended a Python traceback to the upstream error message.
Conditions required
The caller can read /health and a model-health probe fails.
Potential impact
Internal implementation and filesystem details can be exposed to a health endpoint reader.
Affected versions and configurations
The reviewed sources do not establish a complete affected-release range.
Fix and mitigation status
1.109.2 contains the correction. The release also identifies 1.110.0 as carrying it.
Practical next steps
Deploy the correction and restrict health endpoint readership; review provider error text for sensitive content.
Operating lesson
Keep implementation diagnostics in access-controlled server logs.
Evidence and limits
The earliest reviewed public correction is November 16. Tagged 1.109.2 returns the exception message and sends a redacted, truncated traceback to debug logging. Upstream error messages remain visible and may themselves include identifiers.
Sources
- fix(proxy): stop returning stack traces in health check errors
Primary source ·
- v1.109.2 release notes
Primary source ·
- LiteLLM 1.109.2 health error response
Primary source ·