ai-ide-code-exec
OfficialPinpoint AI IDE code-execution risks end-to-end.
System Documentation
What problem does it solve?
Tests AI IDEs for code execution vulnerabilities beyond MCP and terminal filters. Use when assessing hooks abuse, binary planting, IDE settings exploitation, tools definition auto-loading, or environment variable prefixing attack vectors. Patterns are ordered by interaction tier: Tier 1 (zero-interaction) through Tier 4 (trusted workspace + specific action).
Core Features & Use Cases
- Broad vector coverage across hooks abuse, binary planting, IDE settings abuse, tools auto-loading, environment variable prefixing, and safe-executable-with-malicious-config vectors.
- Tiered testing guidance from Tier 1 to Tier 4 for multiple IDE families (VS Code, JetBrains, CLI-based agents, and cloud agents).
- Use cases include security assessments of AI IDEs, reproducing exploit chains, and documenting mitigations for development workflows.
Quick Start
Run a comprehensive assessment of code-execution vectors in AI IDEs, from zero-click to trusted-workspace scenarios, and report actionable findings.
Dependency Matrix
Required Modules
None requiredComponents
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: ai-ide-code-exec Download link: https://github.com/Mindgard/ai-ide-skills/archive/main.zip#ai-ide-code-exec Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.