CVE-2026-63086: Server-Side Request Forgery (SSRF) in huggingface text-generation-inference
text-generation-inference through 3.3.7 contains a server-side request forgery (SSRF) vulnerability in the OpenAI-compatible multimodal chat completions endpoint that allows unauthenticated network attackers to coerce the server into issuing arbitrary HTTP GET requests by supplying a crafted image_url value in chat message content. The fetch_image function in router/src/validation.rs performs no validation of private, loopback, link-local, or cloud metadata target addresses, and the reqwest HTTP client follows redirects by default, enabling attackers to bypass scheme checks via redirect chains to reach internal services and cloud instance-metadata endpoints for internal port scanning and credential theft.
AI Analysis
Technical Summary
CVE-2026-63086 is an SSRF vulnerability in huggingface's text-generation-inference product affecting versions up to 3.3.7. The issue exists in the OpenAI-compatible multimodal chat completions endpoint where the fetch_image function fails to validate target URLs for private, loopback, link-local, or cloud metadata addresses. The reqwest HTTP client used follows redirects by default, allowing attackers to bypass scheme restrictions via redirect chains. This enables unauthenticated remote attackers to coerce the server into issuing arbitrary HTTP GET requests, potentially accessing internal services and cloud instance metadata endpoints for reconnaissance and credential theft.
Potential Impact
An unauthenticated attacker can exploit this SSRF vulnerability to make the server perform arbitrary HTTP GET requests to internal or cloud metadata endpoints. This can facilitate internal network scanning and unauthorized access to sensitive information such as cloud instance credentials. The vulnerability poses a medium severity risk with a CVSS 4.0 score of 6.9.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict network access from the affected service to internal and cloud metadata endpoints where possible to reduce exposure.
CVE-2026-63086: Server-Side Request Forgery (SSRF) in huggingface text-generation-inference
Description
text-generation-inference through 3.3.7 contains a server-side request forgery (SSRF) vulnerability in the OpenAI-compatible multimodal chat completions endpoint that allows unauthenticated network attackers to coerce the server into issuing arbitrary HTTP GET requests by supplying a crafted image_url value in chat message content. The fetch_image function in router/src/validation.rs performs no validation of private, loopback, link-local, or cloud metadata target addresses, and the reqwest HTTP client follows redirects by default, enabling attackers to bypass scheme checks via redirect chains to reach internal services and cloud instance-metadata endpoints for internal port scanning and credential theft.
CVSS v4.0
Score 6.9medium
Affected software
pkg:github/text-generation-inferenceRun 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
CVE-2026-63086 is an SSRF vulnerability in huggingface's text-generation-inference product affecting versions up to 3.3.7. The issue exists in the OpenAI-compatible multimodal chat completions endpoint where the fetch_image function fails to validate target URLs for private, loopback, link-local, or cloud metadata addresses. The reqwest HTTP client used follows redirects by default, allowing attackers to bypass scheme restrictions via redirect chains. This enables unauthenticated remote attackers to coerce the server into issuing arbitrary HTTP GET requests, potentially accessing internal services and cloud instance metadata endpoints for reconnaissance and credential theft.
Potential Impact
An unauthenticated attacker can exploit this SSRF vulnerability to make the server perform arbitrary HTTP GET requests to internal or cloud metadata endpoints. This can facilitate internal network scanning and unauthorized access to sensitive information such as cloud instance credentials. The vulnerability poses a medium severity risk with a CVSS 4.0 score of 6.9.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict network access from the affected service to internal and cloud metadata endpoints where possible to reduce exposure.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-07-15T15:45:44.600Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a5907d068715ace4356cd19
Added to database: 07/16/2026, 16:33:20 UTC
Last enriched: 07/16/2026, 16:48:14 UTC
Last updated: 07/17/2026, 00:57:56 UTC
Views: 8
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.