CVE-2026-45312

Affects: prompt injection

CVSS: CRITICAL · 9.9 v3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Published: 2026-05-29
Weakness: CWE-1336
Source: nvd.nist.gov/vuln/detail/CVE-2026-45312

Description

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine. In 0.24.0 and earlier, a Jinja2 template injection in the prompt generator (rag/prompts/generator.py) allows any authenticated user to execute arbitrary OS commands on the server. Any normal user can register, create a Canvas workflow with a DuckDuckGo + LLM component chain, and trigger the SSTI.

References

https://github.com/infiniflow/ragflow/security/advisories/GHSA-wpg4-h5g2-jxm6

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-45312 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course → · Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming