CVE-2026-82447

Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock

Published Aug 29, 2026 CVSS 4.0 · 8.7 High EPSS < 1% KEV · Not listed
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.

Analysis

AI-generated

Technical impact

Skyvern before version 1.0.45 contains a sandbox escape flaw in the TextPromptBlock component. The vulnerability causes user supplied template fragments to be rendered twice—first within a restricted Jinja environment intended to prevent code execution, and then again in an unsandboxed environment. This double rendering allows an attacker to inject malicious Jinja template syntax via workflow parameters or the output of upstream blocks. When interpreted by the unsandboxed engine, the injected syntax can execute arbitrary code with the full privileges of the server process. The weakness is a form of template forging identified as CWE‑1336 and can lead to complete compromise of the hosting machine.

Affected Systems

The affected product is Skyvern AI’s Skyvern platform before release 1.0.45. Any deployment of Skyvern contained within that version range is vulnerable; versions 1.0.45 and later are considered fixed.

Risk and Exploitability

The severity represented by a CVSS score of 8.7 indicates high risk. While a precise EPSS value is not available, the vulnerability permits code execution without additional authentication, implying a high likelihood of exploitation if an attacker can influence the workflow inputs. The flaw is not listed in the CISA KEV catalog, but its impact and ease of exploitation recommend prompt mitigation. Attackers would typically craft malicious workflow parameters or upstream outputs that include Jinja syntax, then trigger execution of the TextPromptBlock. The ability to execute code at the server level provides full control of the affected environment.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade Skyvern to version 1.0.45 or later to apply the vendor fix.
  • Disable or remove the TextPromptBlock from any custom workflows until a patched version is deployed.
  • Validate and sanitize all workflow parameters and upstream block outputs to ensure they cannot contain Jinja template syntax before rendering.

Generated by OpenCVE AI on August 29, 2026 at 13:21 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Skyvern-ai
Skyvern-ai skyvern
Vendors & Products Skyvern-ai
Skyvern-ai skyvern
Type Values Removed Values Added
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.
Title Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock
Weaknesses CWE-1336
References
Metrics cvssV3_1

{'score': 8.8, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H'}

cvssV4_0

{'score': 8.7, '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'}

Weaknesses
  • CWE-1336

    Improper Neutralization of Special Elements Used in a Template Engine

Sources

Status
PUBLISHED
Assigner
VulnCheck
Published
Updated
Sep 24, 2026, 2:20 PM
Reserved
Aug 29, 2026, 11:37 AM
Status
Deferred
Published
Aug 29, 2026, 1:16 PM
Modified
Sep 23, 2026, 5:17 PM