CVE-2026-63086 (GCVE-0-2026-63086)
Vulnerability from cvelistv5 – Published: 2026-07-16 15:59 – Updated: 2026-07-16 17:41 X_Open Source Unsupported When Assigned- CWE-918 - Server-Side Request Forgery (SSRF)
| URL | Tags |
|---|---|
| https://github.com/geo-chen/oss/blob/main/text-ge… | technical-descriptionexploit |
| https://www.vulncheck.com/advisories/text-generat… | third-party-advisory |
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| huggingface | text-generation-inference |
Affected:
0 , ≤ 3.3.7
(semver)
|
guessed |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-63086",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-16T17:35:08.407194Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-16T17:41:55.297Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "affected",
"product": "text-generation-inference",
"repo": "https://github.com/huggingface/text-generation-inference",
"vendor": "huggingface",
"versions": [
{
"lessThanOrEqual": "3.3.7",
"status": "affected",
"version": "0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "George Chen"
}
],
"datePublic": "2026-07-15T00:00:00.000Z",
"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."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "PRESENT",
"attackVector": "NETWORK",
"baseScore": 6.9,
"baseSeverity": "MEDIUM",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"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",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "NONE",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
},
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-16T16:00:50.233Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "Researcher Disclosure",
"tags": [
"technical-description",
"exploit"
],
"url": "https://github.com/geo-chen/oss/blob/main/text-generation-inference.md"
},
{
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/text-generation-inference-ssrf-via-fetch-image-in-multimodal-chat-completions"
}
],
"source": {
"discovery": "UNKNOWN"
},
"tags": [
"x_open-source",
"unsupported-when-assigned"
],
"title": "text-generation-inference 3.3.7 SSRF via fetch_image in multimodal chat completions",
"x_generator": {
"engine": "vulncheck"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-63086",
"datePublished": "2026-07-16T15:59:45.871Z",
"dateReserved": "2026-07-15T15:45:44.600Z",
"dateUpdated": "2026-07-16T17:41:55.297Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-63086",
"date": "2026-11-15",
"epss": "0.00434",
"percentile": "0.38238"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"defaultStatus": "affected",
"product": "text-generation-inference",
"repo": "https://github.com/huggingface/text-generation-inference",
"vendor": "huggingface",
"versions": [
{
"lessThanOrEqual": "3.3.7",
"status": "affected",
"version": "0",
"versionType": "semver"
}
]
}
],
"source": "disclosure@vulncheck.com"
}
],
"cveTags": [
{
"sourceIdentifier": "disclosure@vulncheck.com",
"tags": [
"unsupported-when-assigned"
]
}
],
"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."
},
{
"lang": "es",
"value": "text-generation-inference hasta la versi\u00f3n 3.3.7 contiene una vulnerabilidad de falsificaci\u00f3n de petici\u00f3n del lado del servidor (SSRF) en el endpoint de finalizaci\u00f3n de chat multimodal compatible con OpenAI que permite a atacantes de red no autenticados forzar al servidor a emitir peticiones HTTP GET arbitrarias al proporcionar un valor image_url manipulado en el contenido del mensaje de chat. La funci\u00f3n fetch_image en router/src/validation.rs no realiza ninguna validaci\u00f3n de direcciones de destino privadas, de bucle invertido, de enlace local o de metadatos de la nube, y el cliente HTTP reqwest sigue las redirecciones por defecto, lo que permite a los atacantes eludir las comprobaciones de esquema a trav\u00e9s de cadenas de redirecci\u00f3n para alcanzar servicios internos y endpoints de metadatos de instancias en la nube para el escaneo de puertos interno y el robo de credenciales."
}
],
"id": "CVE-2026-63086",
"lastModified": "2026-10-24T20:10:00.137",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N",
"version": "3.1"
},
"exploitabilityScore": 3.9,
"impactScore": 4.0,
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
],
"cvssMetricV40": [
{
"cvssData": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "PRESENT",
"attackVector": "NETWORK",
"availabilityRequirement": "NOT_DEFINED",
"baseScore": 6.9,
"baseSeverity": "MEDIUM",
"confidentialityRequirement": "NOT_DEFINED",
"exploitMaturity": "NOT_DEFINED",
"integrityRequirement": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "NONE",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-63086",
"options": [
{
"exploitation": "poc"
},
{
"automatable": "yes"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-16T17:35:08.407194Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-07-16T17:16:58.553",
"references": [
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/geo-chen/oss/blob/main/text-generation-inference.md"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://www.vulncheck.com/advisories/text-generation-inference-ssrf-via-fetch-image-in-multimodal-chat-completions"
}
],
"sourceIdentifier": "disclosure@vulncheck.com",
"vulnStatus": "Deferred",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-918"
}
],
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
]
}
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-63086",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-16T17:35:08.407194Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-16T17:35:11.307Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "affected",
"product": "text-generation-inference",
"repo": "https://github.com/huggingface/text-generation-inference",
"vendor": "huggingface",
"versions": [
{
"lessThanOrEqual": "3.3.7",
"status": "affected",
"version": "0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "George Chen"
}
],
"datePublic": "2026-07-15T00:00:00.000Z",
"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."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "PRESENT",
"attackVector": "NETWORK",
"baseScore": 6.9,
"baseSeverity": "MEDIUM",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"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",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "NONE",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
},
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-16T16:00:50.233Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "Researcher Disclosure",
"tags": [
"technical-description",
"exploit"
],
"url": "https://github.com/geo-chen/oss/blob/main/text-generation-inference.md"
},
{
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/text-generation-inference-ssrf-via-fetch-image-in-multimodal-chat-completions"
}
],
"source": {
"discovery": "UNKNOWN"
},
"tags": [
"x_open-source",
"unsupported-when-assigned"
],
"title": "text-generation-inference 3.3.7 SSRF via fetch_image in multimodal chat completions",
"x_generator": {
"engine": "vulncheck"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-63086",
"datePublished": "2026-07-16T15:59:45.871Z",
"dateReserved": "2026-07-15T15:45:44.600Z",
"dateUpdated": "2026-07-16T17:41:55.297Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
How durations are calculated
Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.
Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.
Loading timeline…
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.