CVE-2026-82447Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock
Updated under an hour ago ()
Does this affect you?
It affects Skyvern-AI skyvern. Add what you run to find out whether that includes you.
No exploitation reported and no EPSS estimate yet.
Do this next
Free account, 1 product
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
- 8.8 HIGH (v3.1, CNA)CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- Weakness (CWE)
- CWE-1336
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- Not loaded for this CVE
- Assigned by
- VulnCheck
- NVD analysis
- Deferred
- Record last updated
- Sep 24, 2026
- First seen by InfoSec Signals
- Oct 9, 2026
Affected products
Skyvern-AI skyvern skyvern_ai:skyvern (from the name) | from 0.2.1 before 1.0.45 | CNA record |
References
- https://github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a3124epatch
- https://github.com/Skyvern-AI/skyvernproduct
- https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/models/block.pytechnical-description
- https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.pytechnical-description
- https://www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-textpromptblockthird-party-advisory
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.