SSRF in Modeltc Lightllm
CVE-2026-103243
LightLLM through 1.2.0 fails to validate image_url and audio_url parameters in multimodal endpoints, allowing unauthenticated attackers to perform server-side request forgery. Attackers can supply arbitrary URLs to fetch internal resources, with vision model processing disclosing content or error responses revealing internal network topology.
Vulnerability class: SSRF (Server-Side Request Forgery)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 5.8 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:N/A:N.
EPSS exploit prediction
EPSS 0.003, 24.2th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
Weakness classification (CWE)
References
- GitHub Issue #1608 (issue-tracking)
- github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/utils/multimodal_utils.py (technical-description)
- github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/multimodal_params.py (technical-description)
- github.com/ModelTC/LightLLM (product)
- VulnCheck Advisory: LightLLM through 1.2.0 Server-Side Request Forgery via multimodal endpoints (third-party-advisory)