CVE-2026-59707: LocalAI POST /models/apply permits unauthenticated server-side request forgery through gallery URLs

Should you act?

Critical and remotely reachable

No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

• Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
• EPSS 0.5%, percentile 41: FIRST’s model estimates a 0.5% chance of exploitation activity in the next 30 days, higher than 41% of all scored CVEs (low). EPSS is a probability, not a verdict.
• Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
• Only applies if your dependency tree includes github.com/mudler/LocalAI (Go) < 1.40.1-0.20260703213242-2cbb3c96b34d, fixed in 1.40.1-0.20260703213242-2cbb3c96b34d. Check your lockfile, including transitive dependencies.

What it is

LocalAI contains an unauthenticated server-side request forgery vulnerability in the POST /models/apply endpoint that allows attackers to fetch arbitrary internal URLs. The endpoint passes unsanitized gallery URL fields directly to gallery.GetGalleryConfigFromURLWithContext without proper validation, enabling attackers to force the server to issue HTTP GET requests to private and loopback ranges with partial response content leaked through error messages.

From the GitHub advisory

LocalAI contains an unauthenticated server-side request forgery vulnerability in the POST /models/apply endpoint that allows attackers to fetch arbitrary internal URLs. The endpoint passes unsanitized gallery URL fields directly to gallery.GetGalleryConfigFromURLWithContext without proper validation, enabling attackers to force the server to issue HTTP GET requests to private and loopback ranges with partial response content leaked through error messages.

Weakness type: CWE-918.

Product: github.com/mudler/LocalAI (Go) · Assigned by: VulnCheck · Published: 2026-07-07

Affected and fixed versions

Severity scores

• Attack vector: network (remotely reachable)
• Attack complexity: low
• Attack requirements: none
• Privileges required: none (no login)
• User interaction: none

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

• CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
• CISA SSVC assessment: exploitation poc, automatable yes, technical impact partial.
• FIRST EPSS (model of 2026-10-21): 0.48% probability of exploitation activity in the next 30 days; percentile 41.

Timeline

• 2026-07-07 — CVE record published by VulnCheck
• 2026-07-07 — GitHub-reviewed advisory GHSA-8c5q-hx4g-qq23 published (critical)
• 2026-09-24 — CVE record last updated

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Vendor and project advisories, patches

1. Patch Commit github.com

Vulnerability records

1. GitHub Advisory GHSA-8c5q-hx4g-qq23 github.com
2. CVE.org record CVE-2026-59707 cve.org
3. NVD entry CVE-2026-59707 nvd.nist.gov

Other references from the CVE record and advisory

1. GitHub Issue github.com
2. Product github.com
3. vulncheck.com vulncheck.com

Critical Go advisories · Today’s Security Digest