CVE-2025-49619

Affects: prompt injection

CVSS: HIGH · 8.5v3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N
Published: 2025-06-07
Weakness: CWE-1336
Source: nvd.nist.gov/vuln/detail/CVE-2025-49619

Description

Skyvern through 0.1.85 is vulnerable to server-side template injection (SSTI) in the Prompt field of workflow blocks such as the Navigation v2 Block. Improper sanitization of Jinja2 template input allows authenticated users to inject crafted expressions that are evaluated on the server, leading to blind remote code execution (RCE).

References

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2025-49619 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