LightLLM through 1.2.0 Server-Side Request Forgery via multimodal endpoints
10Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 6.9
exploitation probability
—
observed exploitation
nono source reports it
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.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:N/VA:N/SC:L/SI:N/SA:N
Affected products
ModelTC · LightLLMReferences
https://github.com/ModelTC/LightLLMhttps://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/multimodal_params.py#L149https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/utils/multimodal_utils.py#L82-L91https://github.com/ModelTC/LightLLM/issues/1608https://www.vulncheck.com/advisories/lightllm-through-1.2.0-server-side-request-forgery-via-multimodal-endpoints