AI Editor Rules

PassAudited by ClawScan on May 10, 2026.

Overview

This is a coherent instruction-only template collection for AI editor rules, with no code or hidden execution, but users should review the templates before copying them into projects.

This skill appears safe to use as a template library. Before copying the rule files into a project, read and adapt them, avoid storing secrets in MEMORY.md or TOOLS.md, keep local memory files out of git, and verify any npm package before installing it globally.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Note

ASI01: Agent Goal Hijack

What this means

The template can affect how an AI coding assistant responds and prioritizes actions in future sessions.

Why it was flagged

If copied into an agent workspace, this template becomes persistent instruction text that changes agent behavior before tasks. This is expected for an AI editor rules template, but users should review it before adoption.

Skill content

## ⚠️ MANDATORY: Before ANY Task

### The 15 Rules

1. **Confirm before executing**

Recommendation

Review and customize the rule file before placing it in a project or agent workspace.

Note

ASI04: Agentic Supply Chain Vulnerabilities

What this means

Installing a global npm package can affect the local development environment.

Why it was flagged

The skill recommends a user-directed global npm package install for format conversion. This is purpose-aligned, but the artifact does not pin a version or provide package provenance.

Skill content

npm install -g crossrule

Recommendation

Verify the crossrule package source and consider pinning a known version before installing it globally.

Note

ASI06: Memory and Context Poisoning

What this means

Sensitive notes or credentials could be stored in project files and later reused, shared, or committed unintentionally.

Why it was flagged

The template encourages persistent local memory files and references credentials-related tool notes. This is visible and user-controllable, but could expose sensitive information if used carelessly or committed to a repository.

Skill content

When someone says "remember this" → write it to a file ... TOOLS.md       # Local tool notes (credentials, quirks, fixes)

Recommendation

Do not store secrets in memory files; keep any local memory files out of version control and define clear rules for what may be remembered.