CVE-2026-82447: Improper Neutralization of Special Elements Used in a Template Engine in Skyvern-AI skyvern
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.
CVSS v4.0
Score 8.7high
Affected software
Skyvern-AI
skyvern
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
Skyvern versions from 0.2.1 up to but not including 1.0.45 contain a vulnerability in the TextPromptBlock where prompts are rendered twice—initially in a sandboxed Jinja environment and subsequently in an unsandboxed environment. This improper neutralization of special elements used in the template engine allows attackers to inject malicious Jinja template syntax through workflow parameters or upstream block output. Successful exploitation results in arbitrary code execution with server process privileges.
Potential Impact
An attacker can execute arbitrary code on the server running the vulnerable Skyvern instance, potentially leading to full compromise of the server process. This elevates the risk of unauthorized access, data theft, or disruption of service. The CVSS 4.0 score of 8.7 (high severity) reflects the network attack vector, low attack complexity, no required privileges beyond limited user privileges, and no user interaction needed.
Mitigation Recommendations
A fixed version of Skyvern is available starting from version 1.0.45. Users should upgrade to version 1.0.45 or later to remediate this vulnerability. No additional mitigation steps are indicated in the provided data.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-08-29T11:37:29.518Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6a92cf1eacd9273b49be6491
Added to database: 08/29/2026, 12:22:54 UTC
Last enriched: 09/25/2026, 02:44:41 UTC
Last updated: 10/13/2026, 18:48:24 UTC
Views: 123
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.