text-generation-inference 3.3.7 SSRF via fetch_image in multimodal chat completions
33Vexday Risk Score
No sign of exploitation. It has a public proof of concept.
ssvc Attendcvss 6.9epss 0.3%
exploitation probability
0.3%top 75% of all CVEs
observed exploitation
nono source reports it
1 public exploit(s)
text-generation-inference through 3.3.7 contains a server-side request forgery (SSRF) vulnerability in the OpenAI-compatible multimodal chat completions endpoint that allows unauthenticated network attackers to coerce the server into issuing arbitrary HTTP GET requests by supplying a crafted image_url value in chat message content. The fetch_image function in router/src/validation.rs performs no validation of private, loopback, link-local, or cloud metadata target addresses, and the reqwest HTTP client follows redirects by default, enabling attackers to bypass scheme checks via redirect chains to reach internal services and cloud instance-metadata endpoints for internal port scanning and credential theft.
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:N
Affected products
huggingface · text-generation-inferencepublic PoCs found — 1
cve_referencegithub.com/geo-chen/oss/blob/main/text-generation-inference.mdunverified⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.