CVE-2026-82447
Medium
Elevated severity or exploit probability.
CVSS base
8.8
HIGH
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
EPSS — probability of exploitation (30 days)
0.8%
53.9th percentile
CISA KEV
Not listed
Weakness / dates
CWE-1336
Published 2026-08-29 · modified 2026-09-23
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.
References
- https://github.com/Skyvern-AI/skyvern
- https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.py
- https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/models/block.py
- https://github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a3124e
- https://www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-textpromptblock