AI Sec Watch: A Security Intelligence Platform for AI Systems

Luu, T.J.

LowVulnerability

GHSA-c693-x898-5g4h: BerriAI litellm has SSRF via Unvalidated spec_path URL in MCP OpenAPI Spec Loader

Source: GitHub Advisory(opens in a new tab)
Identifiers: CVE-2026-12798GHSA-c693-x898-5g4h
Published: June 21, 2026
Record updated: October 10, 2026

View JSON

Affected: litellm <= 1.82.2
Fixed in: No fixed version was stated when the source was last read.
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.4%

Summary

A weakness in BerriAI litellm up to 1.82.2 lies in the load_openapi_spec_async function of litellm/proxy/_experimental/mcp_server/openapi_to_mcp_generator.py, within the MCP OpenAPI Spec Loader component. Manipulating the spec_path argument causes server-side request forgery, and it can be exploited remotely. A public exploit exists, and the vendor was contacted early about the disclosure.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 6.3(low)
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
Attack vector: network
Attack complexity: low
Privileges required: low
User interaction: none
EPSS: 0.4%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on October 10, 2026.
Disclosure date: June 21, 2026

Weaknesses and techniques

Weakness (CWE): CWE-918
Attack pattern (CAPEC): CAPEC-664

Affected

Packages: litellm@<= 1.82.2

Classification

Attack type: Other
Attack sophistication: Trivial
AI component targeted: API
Impact: Confidentiality,
Integrity
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative.

Original source: https://github.com/advisories/GHSA-c693-x898-5g4h

First tracked: October 10, 2026 at 12:52 AM ET, from GitHub Advisory Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 85% (self-assessed)

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

litellmPyPILLM dependency since 2023-07-27 · 54 tracked dependents

Topics

Model Context Protocol

Summary

Mitigation

Affected packages in the Exposure Registry

Topics

Related items