CVE-2026-82447
Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock
- State
- Published
- Severity
- 8.7 High
- Published
- Aug 29, 2026
- Updated
- Sep 24, 2026
- Reserved
- Aug 29, 2026
Description
Skyvern before 1.0.45 contains a sandbox escape vulnerability in TextPromptBlock that renders prompts twice, first through a sandboxed Jinja environment and then through an unsandboxed environment. Attackers can inject malicious Jinja template syntax through workflow parameters or upstream block output to execute arbitrary code with server process privileges.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 4.0 | 8.7 High | CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N | VulnCheck |
| 3.1 | 8.8 High | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | VulnCheck |
Weaknesses
- CWE-1336 Improper Neutralization of Special Elements Used in a Template Engine
Affected Products
| Product | Versions |
|---|---|
skyvernSkyvern-AI |
|
References
- Patch Commitpatch
- https://github.com/Skyvern-AI/skyvernproduct
- Vulnerable code: block.py (sandboxed first render, non-sandboxed second render)technical-description
- Vulnerable code: prompting.py (PromptEngine uses a plain jinja2.Environment)technical-description
- VulnCheck Advisory: Skyvern before 1.0.45 Sandbox Escape via TextPromptBlockthird-party-advisory
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.