CVE-2026-82447
Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock
CVSS Score
8.8
EPSS Score
0.0%
EPSS Percentile
0th
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.
| CWE | CWE-1336 |
| Vendor | skyvern-ai |
| Product | skyvern |
| Published | Aug 29, 2026 |
Stay Ahead of the Next One
Get instant alerts for skyvern-ai skyvern
Be the first to know when new high vulnerabilities affecting skyvern-ai skyvern are published — delivered to Slack, Telegram or Discord.
Get Free Alerts →
Free · No credit card · 60 sec setup
CVSS v3 Breakdown
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High
Affected Versions
Skyvern-AI / skyvern
0.2.1 < 1.0.45
References
github.com: https://github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a3124e github.com: https://github.com/Skyvern-AI/skyvern github.com: https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/models/block.py github.com: https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.py vulncheck.com: https://www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-textpromptblock
Credits
🔍 hayato1121