CVE-2026-63086

HIGHPre-NVD 8.68.6—
EchelonGraph scoreHIGH confidence

Score 8.6 from GitHub Security Advisory published 2026-07-16. a secondary CVSS source baseline 8.6; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: epss, ghsa, secondary
Trending — 3 sources updated this weekElevated
8.6EG
EchelonGraph verdictPlan a fixSerious severity, but no confirmed exploitation yet.
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0%CVSS: 8.6Exploit: Elevated riskExposed: 0

No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.

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 v3
8.6
EG Score
8.6(high)
EG Risk
70(Attend)
EG Risk 70/100SSVC: Attend

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed
Severity86% × 45%
Exploitation40% × 40%
Automatability100% × 15%
Action: Remediate soon — notable exploitation risk.
EPSS PROB
0%
EPSS %ILE
25%
KEV
Not listed

Published

July 16, 2026

Last Modified

July 16, 2026

Advisory Details (2)

Auto-updated Jul 16, 2026
No patch confirmed yet.
generic

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

https://www.vulncheck.com/advisories/text-generation-inference-ssrf-via-fetch-image-in-multimodal-chat-completions
generic

oss/text-generation-inference.md at main · geo-chen/oss · GitHub

https://github.com/geo-chen/oss/blob/main/text-generation-inference.md

Vendor Advisories for CVE-2026-63086(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 16× in last 7d / 22× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.

  1. 2026-07-27 00:11 UTCEG score recompute
  2. 2026-07-27 00:11 UTCGHSA enrichment
  3. 2026-07-26 14:54 UTCEPSS rescore
  4. 2026-07-26 14:54 UTCEPSS rescore
  5. 2026-07-26 11:25 UTCEG score recompute
  6. 2026-07-26 11:25 UTCGHSA enrichment
  7. 2026-07-25 14:18 UTCEPSS rescore
  8. 2026-07-25 14:18 UTCEPSS rescore
  9. 2026-07-24 14:18 UTCEPSS rescore
  10. 2026-07-24 14:18 UTCEPSS rescore
  11. 2026-07-23 14:18 UTCEPSS rescore
  12. 2026-07-23 14:18 UTCEPSS rescore
  13. 2026-07-23 03:22 UTCEG score recompute
  14. 2026-07-22 14:08 UTCEPSS rescore
  15. 2026-07-22 14:08 UTCEPSS rescore
  16. 2026-07-20 17:08 UTCEPSS rescore
  17. 2026-07-19 14:31 UTCEPSS rescore
  18. 2026-07-19 02:29 UTCEPSS rescore
  19. 2026-07-18 10:04 UTCEPSS rescore
  20. 2026-07-17 05:13 UTCGHSA enrichment
  21. 2026-07-16 16:29 UTCEG score recompute
  22. 2026-07-16 16:28 UTCMITRE cvelistV5first tracked

Related CVEs(same CWE)

Frequently asked(5)

What is CVE-2026-63086?
CVE-2026-63086 is a high vulnerability published on July 16, 2026. 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…
When was CVE-2026-63086 disclosed?
CVE-2026-63086 was first published in the National Vulnerability Database on July 16, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-63086 actively exploited?
CVE-2026-63086 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0% probability of exploitation in the next 30 days, which ranks it in the top 75.3% of all scored CVEs.
What is the CVSS score of CVE-2026-63086?
CVE-2026-63086 has a CVSS v3 base score of 8.6 (NVD).
How do I remediate CVE-2026-63086?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-63086, EchelonGraph cross-links them in the Vendor Advisories panel below — those typically contain the canonical remediation steps, fixed version numbers, and any vendor-specific mitigations.

Dependency Blast Radius

Explore the affected products and dependency analysis for CVE-2026-63086

Explore →

Is Your Infrastructure Affected by CVE-2026-63086?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Start Free Scan →Browse All CVEs