CVE-2026-82447
8.7
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
Summary
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.
Affected Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| Skyvern-AI | skyvern | 0.2.1 < 1.0.45 | affected |
Weaknesses
- CWE-1336: Improper Neutralization of Special Elements Used in a Template Engine
References
- https://github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a3124e
- https://github.com/Skyvern-AI/skyvern
- https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/models/block.py
- https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.py
- https://www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-textpromptblock
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.