If you discover a security vulnerability, please report it by emailing fullerbt@users.noreply.github.com.
Do not open a public issue for security vulnerabilities.
This repository contains Claude Code plugins (prompts, skills, agents). These are text-based configuration files that instruct Claude how to behave.
In scope:
- Prompt injection vulnerabilities in skill/agent definitions
- Unsafe bash commands in scripts
- Credential exposure in examples
Out of scope:
- Claude Code CLI vulnerabilities (report to Anthropic)
- General Claude model behavior (report to Anthropic)
We aim to acknowledge reports within 48 hours and provide a fix timeline within 7 days.