The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads and analyzes local project files to provide context-aware code patterns, which introduces a potential attack surface if those files contain malicious instructions. However, this is a standard risk for development-focused skills. * Ingestion points: Local source files including src/entities/player.py and src/config.py. * Boundary markers: None. * Capability inventory: File system read access using Read, Grep, and Glob tools. * Sanitization: None.
[SAFE]: No security issues were detected. All code snippets follow standard Pygame and Python practices, and there are no signs of obfuscation, persistence mechanisms, or unauthorized privilege escalation.

pygame-patterns