HighVulnerabilityLLM-specific

CVE-2026-63086: text-generation-inference SSRF through image_url in chat completions endpoint

Source: NVD(opens in a new tab)
Identifier: CVE-2026-63086
Published: July 16, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.4%

Summary

CVE-2026-63086 affects text-generation-inference through 3.3.7. Its OpenAI-compatible multimodal chat completions endpoint lacks validation in fetch_image (router/src/validation.rs), so an unauthenticated attacker can supply a crafted image_url and make the server send arbitrary HTTP GET requests. Because the reqwest client follows redirects by default, redirect chains can bypass scheme checks and reach private, loopback, link-local and cloud metadata addresses for internal port scanning and credential theft.

Mitigation

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

Details

Scores and exploitation

CVSS score: 8.6(high)
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N
Attack vector: network
Attack complexity: low
Privileges required: none
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 15, 2026.
Disclosure date: July 16, 2026

Weaknesses and techniques

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

Affected

Vendors: HuggingFace

Classification

Attack type: Other
Attack sophistication: Trivial
AI component targeted: Inference
Impact: Confidentiality
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. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-63086

First tracked: July 17, 2026 at 02:08 AM ET, from NVD/CVE Database

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

Classifier confidence: 95% (self-assessed)

Topics

Inference infrastructure

Summary

Mitigation

Topics

Related items