The Agent Skills Directory

[SAFE]: The skill uses standard platform tools including Read, Write, Edit, Grep, and Glob solely for its intended purpose of analyzing and refactoring local source code files.
[SAFE]: The inclusion of npm run test and npm run build in the documentation serves as a recommended verification step to ensure behavior is preserved after simplification, which is a standard and safe development practice.
[SAFE]: The skill presents an attack surface for indirect prompt injection because it reads untrusted data (source code) and has the capability to write or edit files. Evidence: 1. Ingestion points: File reading occurs via Read, Grep, and Glob tools. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present. 3. Capability inventory: The skill can modify files using Write and Edit. 4. Sanitization: No sanitization of the processed code is performed. Despite this surface, the instructions are focused on structural logic changes and do not pose a malicious threat.

simplify-code