Skyvern-AI CVE debriefs

These pages are published after PatchSiren validates generated defensive summaries against stored public CVE and source evidence.

HIGH Skyvern-AI CVE published 2026-08-29

CVE-2026-82447

CVE-2026-82447 is a high-severity vulnerability in Skyvern before version 1.0.45, allowing for sandbox escape via TextPromptBlock. This vulnerability enables attackers to inject malicious Jinja template syntax through workflow parameters or upstream block output, potentially leading to arbitrary code execution with server process privileges. The vulnerability exists due to the double rendering of prompts, [truncated]