Read the docs
TI-2026-45036 Aliases CVE-2026-63086GHSA-c6cx-mj2w-vjcr

text-generation-inference 3.3.7 SSRF via fetch_image in multimodal chat completions

Priority HIGH 70CWE-918Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Attack requirements
Present
Impact type
—
Confidentiality · integrity · availability
None · None · None
Fix status
No fix listed

Attack profile from CVSS 4.0 · CNA. Fix status from CNA.

Summary

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.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00434 37th percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by the CNA
Fix No fix listed No fixed version in the sources yet

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
Automatable
Yes
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
huggingfacetext-generation-inferenceup to 3.3.7—No fix listedCNA
  • text-generation-inference Vendorhuggingface Affected up to 3.3.7 Fixed in — No fix listed CNA

Remediation

No fixed version listed by the sources yet.

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-63086
  2. 2026-10-03 Alias added: GHSA-c6cx-mj2w-vjcr

References

Exploit 1

  • TI-2026-48351 sentence-transformers Arbitrary Code Execution on Local Model Load Despite trust_remote_code=False CVSS 4.0CRITICAL 9.3
  • TI-2026-20914 LeRobot Unsafe Deserialization Remote Code Execution via gRPC CVSS 4.0CRITICAL 9.3
  • TI-2026-04577 Policy Bypass in LightGlue Nested Config Resolution in huggingface/transformers CVSS 3.1CRITICAL 9.6
  • TI-2025-04589 Sandbox Escape Vulnerability in huggingface/smolagents CVSS 3.1CRITICAL 10.0
  • TI-2026-79938 Pickle deserialization in Hugging Face Datasets allows code execution CVSS 4.0HIGH 8.7
  • TI-2026-32710 Diffusers: None.py Trust Remote Code Bypass CVSS 3.1HIGH 8.8
See all 58 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences