43 matches found
skyvern
🐉 Automate Browser-based workflows using LLMs and Computer Vision 🐉 Skyvern automates browser-based workflows using LLMs and computer vision. It provides a Playwright-compatible SDK that adds AI functionality on top of playwright, as well as a no-code workflow builder to help both technical and...
CVE-2025-49619
CVE-2025-49619 PoC This script exploits CVE-2025-49619 in Skyvern to execute a reverse shell command. Author Name: Cristian Branet GitHub: cristibtz Usage 1. Start a listener nc -lvnp 2. Run the exploit python3 exploit.py -u "http://:" -k "" -i -p : Skyvern server IP : Skyvern server port : Your...
skyvern
🐉 Automatiza flujos de trabajo basados en navegador usando LLMs y Visión por Computadora 🐉 Skyvern automatiza flujos de trabajo basados en navegador utilizando LLMs y visión por computadora. Proporciona un SDK compatible con Playwright que añade funcionalidad de IA sobre Playwright, así como un...
skyvern v1.0.55
🐉 Automate Browser-based workflows using LLMs and Computer Vision 🐉 Skyvern automates browser-based workflows using LLMs and computer vision. It provides a Playwright-compatible SDK that adds AI functionality on top of playwright, as well as a no-code workflow builder to help both technical and...
skyvern v1.0.52
🐉 Automate Browser-based workflows using LLMs and Computer Vision 🐉 Skyvern automates browser-based workflows using LLMs and computer vision. It provides a Playwright-compatible SDK that adds AI functionality on top of playwright, as well as a no-code workflow builder to help both technical and...
CVE-2026-82447
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...
CVE-2026-82447 Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock
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...
CVE-2026-82447
Skyvern versions prior to 1.0.45 contain a sandbox escape vulnerability in the TextPromptBlock component. The root cause is a double-rendering flaw: prompts are first processed through a sandboxed Jinja environment and then re-processed through an unsandboxed one. An attacker with low privileges ...
CVE-2026-82447 Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock
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...
EUVD-2026-68096
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...
CVE-2026-82447 Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock
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...
CVE-2026-82447
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...
CVE-2026-82447: Improper Neutralization of Special Elements Used in a Template Engine
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...
PT-2026-83426
Name of the Vulnerable Software and Affected Versions Skyvern versions prior to 1.0.45 Description A sandbox escape exists in the TextPromptBlock component. The issue occurs because prompts are rendered twice: first within a sandboxed Jinja environment and subsequently through an unsandboxed...
skyvern v1.0.50
🐉 Automate Browser-based workflows using LLMs and Computer Vision 🐉 Skyvern automates browser-based workflows using LLMs and computer vision. It provides a Playwright-compatible SDK that adds AI functionality on top of playwright, as well as a no-code workflow builder to help both technical and...
skyvern v1.0.48
🐉 Automate Browser-based workflows using LLMs and Computer Vision 🐉 Skyvern automates browser-based workflows using LLMs and computer vision. It provides a Playwright-compatible SDK that adds AI functionality on top of playwright, as well as a no-code workflow builder to help both technical and...
Skyvern Panel - Detect
Skyvern is an open-source AI agent that automates browser-based workflows using LLMs and computer vision !/usr/bin/env python3 -- coding: utf-8 -- """Skyvern is an open-source AI agent that automates browser-based workflows using LLMs and computer vision.""" from kittysploit import from...
chalkdf (>=1.3.4, <=3.34.2), chalkpy (>=2.72.8, <=2.81.3) +9 more potentially affected by CVE-2026-50271 via ddtrace (2.21.12)
ddtrace PYPI version 2.21.12 is affected by a known vulnerability. The following packages have a transitive dependency on ddtrace and may be impacted: - chalkdf =1.3.4, =2.72.8, =1.17.0, =0.7.5, =0.7.5, =0.7.5, =0.1.53, =9.3.0, =4.2.0, =5.1.0 Source cves: CVE-2026-50271 Source advisory:...
