Back to overview

CVE-2026-59820

MEDIUM
6.1
CVSS 4.0
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.

Metadata

CVE ID
CVE-2026-59820
State
PUBLISHED
Assigner
GitHub_M
Reserved
2026-07-07 15:00 UTC
Published
2026-07-08 19:32 UTC
Last updated
2026-07-09 14:37 UTC
Primary CWE
CWE-22
CWE-22: Improper Limitation of a Pathname to a Restricted Di…
Vendor / Product
BerriAI / litellm
Sources
cve.org  ·  NVD

Severity & Metrics

6.1 MEDIUM CVSS 4.0
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
SSVC — CISA Coordinator
Exploitation
none
Automatable
no
Tech. Impact
total
Affected products (1)
VendorProductPlatformVersions
BerriAI litellm — < 1.83.7-stable
Weakness (CWE)
CWESourceDescription
CWE-22 cna CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
CVSS scores (1)
ScoreSeverityVersionSourceVector
6.1 MEDIUM 4.0 cna 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 (4)
Back to overview