AIKIDO-2026-680474
inference is vulnerable to Server-Side Request Forgery (SSRF)
86
High Risk
This Affects:
inferenceTL;DR
The core image-loading path fetches images from caller-supplied URLs and validates only the hostname string, without resolving the host and while following redirects without re-validating each hop. An attacker who can supply an image URL can steer the server into fetching internal resources such as cloud metadata endpoints, loopback services, and private or link-local hosts, either directly, via a hostname that resolves to a private address, via a redirect, or via DNS rebinding. This exposes internal services and cloud credentials through server-side request forgery. The fix adds resolved-IP validation with connection pinning to the validated address and per-hop redirect re-validation.
Who does this affect?
You are affected if you are using a version that falls within the vulnerable range and your deployment loads images from caller-supplied URLs.
Background info
inference is vulnerable to Server-Side Request Forgery (SSRF) in versions 0.8.0 - 1.3.4.
How to fix this
Upgrade the inference library to the patch version.
Are You Affected?
Connect your repositories to instantly see whether vulnerable or malicious packages exist in your codebase.
Free. No credit card required.
I consent to receiving marketing communications based on Aikido’s Privacy Policy.
SOC 2Compliant
ISO 27001CompliantISO 42001Compliant
FedRAMPImplementing© All Intel data is openly available and commercially licensed.