CVE-2026-12798: Server-Side Request Forgery in BerriAI litellm
A weakness has been identified in BerriAI litellm up to 1.82.2. Affected by this vulnerability is the function load_openapi_spec_async of the file litellm/proxy/_experimental/mcp_server/openapi_to_mcp_generator.py of the component MCP OpenAPI Spec Loader. This manipulation of the argument spec_path causes server-side request forgery. It is possible to initiate the attack remotely. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early about this disclosure.
AI Analysis
Technical Summary
BerriAI litellm versions 1.82.0 through 1.82.2 contain a server-side request forgery vulnerability in the load_openapi_spec_async function of the MCP OpenAPI Spec Loader component. This vulnerability arises from improper validation of the spec_path argument, enabling remote attackers to coerce the server into making unauthorized requests. The vulnerability is remotely exploitable and publicly disclosed. The vendor has been notified but has not yet released an official fix or mitigation. The CVSS 4.0 vector indicates network attack vector, low attack complexity, no privileges or user interaction required, and low to low impact on confidentiality, integrity, and availability.
Potential Impact
Successful exploitation of this vulnerability allows an attacker to make the affected server perform arbitrary HTTP requests to internal or external systems, potentially bypassing firewall restrictions or accessing sensitive internal resources. The impact is rated medium due to limited confidentiality, integrity, and availability consequences as per the CVSS vector. No known active exploitation has been reported.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is released, users should consider restricting network access to the vulnerable component and carefully validate or sanitize inputs to the load_openapi_spec_async function if possible. Monitor vendor channels for updates and apply patches promptly once available.
CVE-2026-12798: Server-Side Request Forgery in BerriAI litellm
Description
A weakness has been identified in BerriAI litellm up to 1.82.2. Affected by this vulnerability is the function load_openapi_spec_async of the file litellm/proxy/_experimental/mcp_server/openapi_to_mcp_generator.py of the component MCP OpenAPI Spec Loader. This manipulation of the argument spec_path causes server-side request forgery. It is possible to initiate the attack remotely. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early about this disclosure.
CVSS v4.0
Score 5.3medium
Affected software
cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
BerriAI litellm versions 1.82.0 through 1.82.2 contain a server-side request forgery vulnerability in the load_openapi_spec_async function of the MCP OpenAPI Spec Loader component. This vulnerability arises from improper validation of the spec_path argument, enabling remote attackers to coerce the server into making unauthorized requests. The vulnerability is remotely exploitable and publicly disclosed. The vendor has been notified but has not yet released an official fix or mitigation. The CVSS 4.0 vector indicates network attack vector, low attack complexity, no privileges or user interaction required, and low to low impact on confidentiality, integrity, and availability.
Potential Impact
Successful exploitation of this vulnerability allows an attacker to make the affected server perform arbitrary HTTP requests to internal or external systems, potentially bypassing firewall restrictions or accessing sensitive internal resources. The impact is rated medium due to limited confidentiality, integrity, and availability consequences as per the CVSS vector. No known active exploitation has been reported.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is released, users should consider restricting network access to the vulnerable component and carefully validate or sanitize inputs to the load_openapi_spec_async function if possible. Monitor vendor channels for updates and apply patches promptly once available.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-06-20T17:12:20.743Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a37b9055ae2df37ef7fc32a
Added to database: 06/21/2026, 10:12:21 UTC
Last enriched: 06/28/2026, 21:52:49 UTC
Last updated: 08/04/2026, 20:03:21 UTC
Views: 71
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.