LMDeploy - Server-Side Request Forgery
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in the vision-language module. The load_image() function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating internal or private IP addresses, allowing unauthenticated attackers to access cloud metadata services, internal networks, and sensitive resources via the image_url parameter in /v1/chat/completions requests. References: https://github.com/advisories/GHSA-6w67-hwm5-92mq https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq https://nvd.nist.gov/vuln/detail/CVE-2026-33626 Remediation: Upgrade LMDeploy to version 0.12.3 or later where URL validation via _is_safe_url() blocks requests to non-globally-routable IP addresses.
Used 20 times · 10 assets checked · domain, subdomain, ipv4