{"id":"CVE-2026-63086","state":"PUBLISHED","title":"text-generation-inference 3.3.7 SSRF via fetch_image in multimodal chat completions","description":"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.","publishedAt":"2026-07-16T15:59:45.871Z","updatedAt":"2026-07-16T17:41:55.297Z","severity":{"score":6.9,"label":"Medium","version":"4.0","vector":"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","source":"VulnCheck"},"assigner":"VulnCheck","products":["huggingface text-generation-inference"],"affected":[{"vendor":"huggingface","product":"text-generation-inference","defaultStatus":"affected","versions":[{"version":"0","status":"affected","lessThanOrEqual":"3.3.7","versionType":"semver"}],"repo":"https://github.com/huggingface/text-generation-inference"}],"references":["https://github.com/geo-chen/oss/blob/main/text-generation-inference.md","https://www.vulncheck.com/advisories/text-generation-inference-ssrf-via-fetch-image-in-multimodal-chat-completions"],"weaknesses":["CWE-918"],"ingestedAt":"2026-10-29T20:12:41.951Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2026/63xxx/CVE-2026-63086.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-63086","state":"PUBLISHED","datePublished":"2026-07-16T15:59:45.871Z","dateUpdated":"2026-07-16T17:41:55.297Z","assignerShortName":"VulnCheck","assignerOrgId":"83251b91-4cc7-4094-a5c7-464a1b83ea10","dateReserved":"2026-07-15T15:45:44.600Z"},"containers":{"cna":{"title":"text-generation-inference 3.3.7 SSRF via fetch_image in multimodal chat completions","descriptions":[{"lang":"en","value":"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."}],"affected":[{"vendor":"huggingface","product":"text-generation-inference","defaultStatus":"affected","versions":[{"version":"0","status":"affected","lessThanOrEqual":"3.3.7","versionType":"semver"}],"repo":"https://github.com/huggingface/text-generation-inference"}],"references":[{"url":"https://github.com/geo-chen/oss/blob/main/text-generation-inference.md","name":"Researcher Disclosure","tags":["technical-description","exploit"]},{"url":"https://www.vulncheck.com/advisories/text-generation-inference-ssrf-via-fetch-image-in-multimodal-chat-completions","tags":["third-party-advisory"]}],"metrics":[{"format":"CVSS","scenarios":[{"lang":"en","value":"GENERAL"}],"cvssV4_0":{"attackVector":"NETWORK","attackComplexity":"LOW","attackRequirements":"PRESENT","privilegesRequired":"NONE","userInteraction":"NONE","vulnConfidentialityImpact":"NONE","subConfidentialityImpact":"HIGH","vulnIntegrityImpact":"NONE","subIntegrityImpact":"NONE","vulnAvailabilityImpact":"NONE","subAvailabilityImpact":"NONE","exploitMaturity":"NOT_DEFINED","Safety":"NOT_DEFINED","Automatable":"NOT_DEFINED","Recovery":"NOT_DEFINED","valueDensity":"NOT_DEFINED","vulnerabilityResponseEffort":"NOT_DEFINED","providerUrgency":"NOT_DEFINED","version":"4.0","baseSeverity":"MEDIUM","baseScore":6.9,"vectorString":"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"}},{"format":"CVSS","scenarios":[{"lang":"en","value":"GENERAL"}],"cvssV3_1":{"attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"NONE","scope":"CHANGED","confidentialityImpact":"HIGH","integrityImpact":"NONE","availabilityImpact":"NONE","version":"3.1","baseSeverity":"HIGH","baseScore":8.6,"vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-918","lang":"en","description":"Server-Side Request Forgery (SSRF)","type":"CWE"}]}],"providerMetadata":{"shortName":"VulnCheck","orgId":"83251b91-4cc7-4094-a5c7-464a1b83ea10","dateUpdated":"2026-07-16T16:00:50.233Z"},"tags":["x_open-source","unsupported-when-assigned"],"datePublic":"2026-07-15T00:00:00.000Z","credits":[{"lang":"en","value":"George Chen","type":"finder"}],"source":{"discovery":"UNKNOWN"},"x_generator":{"engine":"vulncheck"}},"adp":[{"title":"CISA ADP Vulnrichment","metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-07-16T17:35:08.407194Z","id":"CVE-2026-63086","options":[{"Exploitation":"poc"},{"Automatable":"yes"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2026-07-16T17:41:55.297Z"}}]}}}