The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to override agent behavior or bypass safety guidelines. The content is instructional and follows development best practices.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file access, or unauthorized network operations detected. The security.md file explicitly provides guidance on protecting sensitive data and avoiding its inclusion in URLs.
[Remote Code Execution] (SAFE): No remote script downloads or piped execution patterns (e.g., curl | bash) are present. Code snippets are for documentation and internal component logic.
[Obfuscation] (SAFE): All files are written in clear, human-readable markdown and TypeScript. No Base64, zero-width characters, or other encoding techniques were found.
[Persistence Mechanisms] (SAFE): No attempts to modify system startup files, shell profiles, or scheduled tasks were identified.
[Command Execution] (SAFE): The skill defines allowed-tools as Read, Grep, Glob. The grep patterns provided in the checklist items are static search patterns for code auditing and do not execute untrusted or dynamic shell input.

react-skills