skill-security-lint

Community

Security lint for skill definitions.

Authorpaulingham
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill scans changed skill definitions and helper libraries to identify prompt-injection patterns, hardcoded secrets, and over-broad tool grants, helping security engineers catch exploitable configurations before they ship.

Core Features & Use Cases

  • Prompt-injection pattern detection within SKILL.md and related prose.
  • Secret detection for credentials, API keys, and tokens in skill files.
  • Evaluation of tool-grants and permissions declared in frontmatter to prevent over-broad access.
  • Returns a structured findings report for integration into OWASP assessments.

Quick Start

Scan the diff for changes in skills/** and SKILL.md and report any prompt-injection, secret, or tool-grant findings.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: skill-security-lint
Download link: https://github.com/paulingham/.claude/archive/main.zip#skill-security-lint

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 545,000+ vetted skills library on demand.