Skip to main content
databaseVerified

sandbox-escape-techniques

by @yaklanghack-skills
Global351.3k
GotBurnout Community0

Description

Official sandbox escape techniques capability by @yaklang. Streamlines autonomous database tasks and workflows.
Quick Agent Installation
Select environment:
$npx skills add https://github.com/yaklang/hack-skills --skill sandbox-escape-techniques

Run this command in your terminal or agent shell

Tags & Topics

#database#backend
README badge
GotBurnout installs badge
[![GotBurnout](https://gotburnout.io/api/badge/skill/yaklang-hack-skills-sandbox-escape-techniques)](https://gotburnout.io/en/skills/yaklang-hack-skills-sandbox-escape-techniques)

Skill Documentation (SKILL.md)

View on GitHub

Related AI Agent Skills

hack367.5k ⬇

Official hack capability by @yaklang. Streamlines autonomous ai-agents tasks and workflows.

@yaklangLearn more →
code-obfuscation-deobfuscation362.3k ⬇

Official code obfuscation deobfuscation capability by @yaklang. Streamlines autonomous ai-agents tasks and workflows.

@yaklangLearn more →
api-sec361.1k ⬇

Official api sec capability by @yaklang. Streamlines autonomous backend tasks and workflows.

@yaklangLearn more →
ssrf-server-side-request-forgery359.4k ⬇

Official ssrf server side request forgery capability by @yaklang. Streamlines autonomous backend tasks and workflows.

@yaklangLearn more →

Related Ecosystem Resources

Explore practical workflows, core terminology, and engineering tools

Glossary Concept

MCP Server

A software service or background process that implements the MCP specification, providing external AI clients with standardized access to function execution, resource reading, and prompt templates.

Glossary Concept

Vector Metadata Filtering & Hybrid Routing

This technology combines semantic vector search with strict deterministic SQL/NoSQL filters on fields (tenant_id, version, role, date) before calculating vector distances.

Practical Guide

Claude Code: Feature Map — From Concepts to 80+ Practical Techniques

claude-code-best-practice is a structured feature map for Claude Code: a single entry point that aggregates core primitives, fresh beta features, and working patterns in one place.

Practical Guide

How to Make AI Agents Safe: Stop Rules, Human Approval, and Sandboxes

An agent in production is a process that can write files, make API calls, change data, and consume tokens autonomously, without pausing and without your involvement at every step.

News

Open-source method enables 6K image generation for Qwen Image, Ideogram, and Flux

A new open-source method supports creating images at very high resolutions, up to 6K, across several popular generation models.

News

Reduce Claude Code token usage with /autocompact 400k

Lowering Claude Code’s auto-compact threshold to 400k tokens keeps conversation history smaller and can significantly reduce token consumption during long sessions.

Slug: yaklang-hack-skills-sandbox-escape-techniques
GitHub