All reports
Medium

LiteLLM: Arbitrary file write via path traversal in Skills archive extraction

Affected versions

Version ranges need review.

Affected versions
< 1.83.7
Fixed version
1.83.7
Affected versions
<1.83.7
Fixed version
1.83.7
Affected versions
Unknown
Fixed version
Not reported

Exploitation

CVE-2026-59820

Probability of exploitation in the next 30 days: 0.59%

FIRST EPSS · 2026-11-21

Description

Impact

LiteLLM Skills archive extraction did not sufficiently validate file paths from uploaded skill ZIP archives. 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, could upload a crafted skill archive containing path traversal entries.

When the skill was processed for execution, those entries could be written outside the intended extraction/staging directory. This could allow arbitrary file write and may lead to code execution depending on deployment configuration and writable paths.

Patches

The issue is fixed in 1.83.7-stable.

LiteLLM recommens upgrading to 1.83.7-stable or later.

Workarounds

If upgrading is not immediately possible:

  1. Block POST /v1/skills at your reverse proxy or API gateway.

  2. Restrict Skills API access to trusted users only.

Links