Vulnerability 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.
CVSS Score
HIGH
Related Weaknesses (CWE)
References
- https://github.com/Skyvern-AI/skyvern
- https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.p
- https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/mo
- https://github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a
- https://www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-te
FAQ
What is CVE-2026-82447?
CVE-2026-82447 is a vulnerability with a CVSS score of 8.8 (HIGH). 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. At...
How severe is CVE-2026-82447?
CVE-2026-82447 has been rated HIGH with a CVSS base score of 8.8/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-82447?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.