Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock
Priority MEDIUM 41CWE-1336Published · Updated
Key facts
- Attack vector
- Network
- Privileges required
- Low
- User interaction
- None
- Attack complexity
- Low
- Attack requirements
- None
- Impact type
- Code execution
- Confidentiality · integrity · availability
- High · High · High
- Fix status
- Fixed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-1336.
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.
Why it matters now
Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00775 56th percentileScored 2026-11-07
Fix Fixed skyvern (Skyvern-AI): 1.0.45
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- No
- Technical impact
- Total
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| Skyvern-AI | skyvern | 0.2.1 to before 1.0.45 | 1.0.45 | Patch available | CNA |
- skyvern VendorSkyvern-AI Affected 0.2.1 to before 1.0.45 Fixed in 1.0.45 Patch available CNA
Remediation
- Fix · CNA skyvern (Skyvern-AI) Fixed in 1.0.45
Timeline
- 2026-10-02 Threatist record created from CVE-2026-82447
- 2026-10-03 Alias added: GHSA-57gg-9j2p-5v4x
References
More Skyvern-AI vulnerabilities
- TI-2026-85963 Sandbox bypass in Skyvern script execution lets users run code on server CVSS 4.0HIGH 8.7
Sources
- CVE-2026-82447 · CVE Program
- CVE-2026-82447 · NVD
- FIRST EPSS
- GHSA-57gg-9j2p-5v4x · GitHub Advisory Database · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences