Home

Description

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.7-stable, LiteLLM Skills archive extraction did not sufficiently validate file paths from uploaded skill ZIP archives, allowing an authenticated user with access to LiteLLM LLM API routes or a key whose allowed_routes includes /v1/skills, anthropic_routes, or llm_api_routes to upload a crafted skill archive containing path traversal entries that could be written outside the intended extraction or staging directory. This issue is fixed in version 1.83.7-stable.

PUBLISHED Reserved 2026-07-07 | Published 2026-07-08 | Updated 2026-07-09 | Assigner GitHub_M




MEDIUM: 6.1CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:N/SI:N/SA:N

Problem types

CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')

Product status

< 1.83.7-stable
affected

References

github.com/...itellm/security/advisories/GHSA-5jmr-gcrj-2c9q

github.com/BerriAI/litellm/pull/25475

github.com/...ommit/6a15adcd64137d37f73dee76dfe7481f8c2d9196

github.com/BerriAI/litellm/releases/tag/v1.83.7-stable

cve.org (CVE-2026-59820)

nvd.nist.gov (CVE-2026-59820)

Download JSON