# CVE-2026-49951: RAGFlow server-side request forgery in LLM API key endpoint

Source: https://junglewise.ai/threats/cve-2026-49951-ragflow-before-0-27-0-contains-a-server-side-request-forgery  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-11-06. Updated: 2026-11-06  
License: CC BY 4.0 with a link back

CVE-2026-49951 · Severity: medium · CVSS 6.3 · Published 2026-11-06

RAGFlow is an AI document processing platform that uses large language models for knowledge extraction and retrieval. Before version 0.27.0, authenticated users could trick the server into making requests to internal services like databases and caches by manipulating an API endpoint, potentially exposing sensitive service details and enabling attacks on internal infrastructure.

Technologies: [InfiniFlow RAGFlow](https://junglewise.ai/threats/technologies/ragflow). Vendors: [InfiniFlow](https://junglewise.ai/threats/vendors/infiniflow).

## Quick answers

**Is CVE-2026-49951 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-49951 being exploited in the wild.

**How severe is CVE-2026-49951?** Medium severity, with a CVSS score of 6.3, published 6 November 2026.

**Which products and versions are affected?** InfiniFlow RAGFlow before 0.27.0.

**Is there a fix for CVE-2026-49951?** Yes: fixed in 0.27.0. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-49951 attacked?** It is attacked over the network.

**Am I affected by CVE-2026-49951?** Check whether you run InfiniFlow RAGFlow at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- Fixed in 0.27.0

## Technical details

The vulnerability is a server-side request forgery (SSRF) in the POST /v1/llm/set_api_key endpoint (set_api_key() in api/apps/llm_app.py) that fails to validate the base_url parameter. An authenticated attacker can supply an arbitrary URL, causing the server to issue requests to internal endpoints. Raw exception text in responses leaks service fingerprints, open ports, and configuration details, enabling reconnaissance of MySQL, Elasticsearch, Redis, MinIO, and other backend services.

## Affected products

- Infiniflow RAGFlow before 0.27.0

## Timeline

- 2026-11-06: disclosed
- 2026-07-31: patched

## References

- [https://github.com/infiniflow/ragflow/commit/b058229ab3a79cc2d61bc1724c2e120ce2ede46d](https://github.com/infiniflow/ragflow/commit/b058229ab3a79cc2d61bc1724c2e120ce2ede46d)
- [https://github.com/infiniflow/ragflow/pull/17641](https://github.com/infiniflow/ragflow/pull/17641)

## Related threats

- [InfiniFlow RAGFlow server-side request forgery in Seafile Connector](https://junglewise.ai/threats/cve-2026-121927-a-vulnerability-has-been-found-in-infiniflow-ragflow-up-to-0-27)
- [InfiniFlow RAGFlow authorization bypass in Text To SQL Retrieval](https://junglewise.ai/threats/cve-2026-121585-a-security-flaw-has-been-discovered-in-infiniflow-ragflow-up-to)
- [RAGFlow authorization bypass in OpenAI-compatible agent completion](https://junglewise.ai/threats/cve-2026-119337-ragflow-is-an-open-source-rag-retrieval-augmented-generation)
- [RAGFlow improper access control in get_dataset API endpoint](https://junglewise.ai/threats/cve-2026-51897-ragflow-0-24-0-contains-improper-access-control-in-get-dataset)
- [infiniflow RAGFlow improper access control in resume API](https://junglewise.ai/threats/cve-2026-51896-infiniflow-ragflow-0-25-3-contains-improper-access-control-in)