ai-ide-recon

Map attack surfaces of AI-assisted IDEs with tier-annotated reports.

61|8|Updated Feb 16, 2026
One-click install
npx skills add https://github.com/Mindgard/ai-ide-skills --skill ai-ide-recon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-ide-recon
Source: https://github.com/Mindgard/ai-ide-skills/tree/main/skills/ai-ide-recon
Command: npx skills add https://github.com/Mindgard/ai-ide-skills --skill ai-ide-recon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Maps the attack surface of AI-assisted IDEs before vulnerability testing, helping security teams prioritize risks and reduce wasted effort.

Core Features & Use Cases

  • Tiered interaction mapping and risk prioritization to focus tests on zero-click and agent-mediated vectors.
  • Discovery of documentation blind spots and auto-load/config files that influence IDE behavior.
  • Output feeds into subsequent pattern-specific skills (mcp-config-poisoning, terminal-filter-bypass, ai-ide-data-exfil, etc.) for end-to-end testing.

Quick Start

Run this recon skill against a target workspace to generate a tiered attack surface map that guides subsequent vulnerability testing.

Frequently Asked Questions about ai-ide-recon

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I map the attack surface of an AI-assisted IDE before vulnerability testing?

Identify the AI IDE attack surface by discovering config paths, auto-load files, and trust boundaries to produce a tier-annotated surface map. This map prioritizes risks like zero-click and agent-mediated vectors to focus subsequent vulnerability testing efforts.

What is a tiered attack surface map for AI IDEs?

A tiered attack surface map is a structured report detailing discovered workspace config paths, trust boundaries, and approval requirements. It categorizes interaction vectors by risk tier to prioritize vulnerability testing on zero-click and agent-mediated threats.

How do I find documentation blind spots and auto-load files that influence AI IDE behavior?

Find documentation blind spots and auto-load configurations by executing a workspace recon scan. The process discovers hidden config paths and trust boundaries that influence AI IDE behavior, outputting a structured report to inform remediation plans.

Does AI IDE attack surface recon work on both open-source and closed-source targets?

Yes, AI IDE attack surface recon applies to both open-source and closed-source targets. It maps interaction tiers and discovers auto-load configurations across diverse environments to reduce wasted testing effort.

What is the best way to prioritize zero-click and agent-mediated vulnerability vectors in AI IDEs?

Prioritize zero-click and agent-mediated vectors by generating a tier-annotated surface map. This approach highlights high-risk interaction paths and workspace trust boundaries to focus pattern-specific vulnerability testing.

What should I do after mapping the AI IDE attack surface?

After mapping the AI IDE attack surface, feed the structured report into pattern-specific vulnerability testing skills. The output directly informs subsequent testing for mcp-config-poisoning, terminal-filter-bypass, and ai-ide-data-exfil vectors.