Vulnerability · Published Jul 8, 2026 · Assigned by GitHub_M

CVE-2026-59820LiteLLM: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')

Medium 6.1

In plain English

A medium-severity path traversal in litellm from BerriAI. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 48% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 4.0)6.1Medium

Exploit odds (30 days)0.6%top 51.8% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	litellm	1.83.7	GHSA-5jmr-gcrj-2c9q
PyPI	litellm	1.83.7	PYSEC-2026-3477

Affected products (as reported)

Vendor	Product	Versions
BerriAI	litellm	< 1.83.7-stable

Weakness: CWE-22 · Vector: CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:N/SI:N/SA:N

References

https://github.com/BerriAI/litellm/security/advisories/GHSA-5jmr-gcrj-2c9q x_refsource_CONFIRM
https://github.com/BerriAI/litellm/pull/25475 x_refsource_MISC
https://github.com/BerriAI/litellm/commit/6a15adcd64137d37f73dee76dfe7481f8c2d9196 x_refsource_MISC
https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable x_refsource_MISC