CVE-2026-82447
Skyvern before 1.0.45 contains a sandbox escape vulnerability in …
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.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/Skyvern-AI/skyvern
- github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.py
- github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/models/block.py
- github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a3124e
- www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-textpromptblock
- nvd.nist.gov/vuln/detail/CVE-2026-82447
- cve.org/CVERecord?id=CVE-2026-82447
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.