The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard shell commands (such as ls, find, cat, and grep) to analyze the repository structure and content. This is a standard and necessary function for the skill's purpose of extracting development conventions and repo-specific rules.
[COMMAND_EXECUTION]: The skill includes and executes a local Python script scripts/test_glob_pattern.py to validate glob patterns against the repository's files. Analysis of the script confirms it uses standard libraries (pathlib, fnmatch) and performs only local, read-only file system operations to count matches, with built-in limits to prevent excessive processing.
[SAFE]: The skill processes repository content (code, configuration, and documentation) to generate instructions. While this creates a surface for indirect prompt injection if the repository contains malicious instructions, the skill is intended as a developer tool, and the risk is considered inherent to the task of repository analysis. No specific vulnerabilities were identified in how the skill handles this data.

generate-path-instructions