Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:NCVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.
Summary
CVE-2026-35486 is a high-severity SSRF (CWE-918) vulnerability in Oobabooga Text Generation Web Ui. Its CVSS base score is 7.5 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 33th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as LLM Application Platforms; in the Privacy and Disclosure risk domain.
The strongest mitigations our analysis identified map to AC-4 (Information Flow Enforcement) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2026-35486 is a server-side request forgery (SSRF) vulnerability, classified under CWE-918, affecting the open-source text-generation-webui, a web interface for running large language models. In versions prior to 4.3, the superbooga and superboogav2 Retrieval-Augmented Generation (RAG) extensions fetch user-supplied URLs using requests.get() without any validation, including no scheme checks, IP filtering, or hostname allowlists. This allows arbitrary HTTP requests to internal or external resources. The vulnerability carries a CVSS v3.1 base score of 7.5 (AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N), highlighting high confidentiality impact with no requirements for authentication or user interaction.
A remote, unauthenticated attacker can exploit this by supplying malicious URLs through the RAG extensions, tricking the server-side application into making requests to attacker-controlled endpoints. Successful exploitation enables access to cloud metadata services (such as those exposing IAM credentials), internal network probing, and service enumeration. The fetched content is then exfiltrated via the RAG pipeline, potentially leaking sensitive data like credentials or internal configurations to the attacker.
The official GitHub security advisory (GHSA-jvrj-w5hq-6cp2) confirms the issue is fully resolved in text-generation-webui version 4.3, which introduces proper URL validation. Security practitioners should immediately upgrade affected instances to 4.3 or later and review logs for suspicious RAG extension usage, particularly in cloud-hosted deployments running large language models.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-19671
Vulnerability Data
text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, he superbooga and superboogav2 RAG extensions fetch user-supplied URLs via requests.get() with zero validation — no scheme check, no IP filtering, no hostname allowlist. An attacker…
more
can access cloud metadata endpoints, steal IAM credentials, and probe internal services. The fetched content is exfiltrated through the RAG pipeline. This vulnerability is fixed in 4.3.
- CWE(s)
AI Security AnalysisAI
- AI Category
- LLM Application Platforms
- Risk Domain
- Privacy and Disclosure
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: rag pipeline, text-generation-webui
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.3.6V1.5.3V5.3.2V10.4.7
Mitigating Controls (NIST 800-53 r5) AI
Information flow enforcement can restrict which destinations the server is allowed to contact on behalf of users.
Input validation directly stops untrusted URLs from being accepted and fetched without destination checks.
Boundary protection limits the network reach of server-initiated requests even if SSRF occurs.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure development practices directly include input validation and destination allow-listing that prevent SSRF.
Runtime monitoring of web applications and services can detect anomalous outbound requests indicative of SSRF.
Vulnerability identification processes can discover and record SSRF flaws in web applications.
Network segmentation and egress controls can limit the damage from successful SSRF requests.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Operational threat data describing SSRF campaigns can be used to tighten outbound-request allow-lists and detection rules before attackers exploit them.