The Agent Skills Directory

[SAFE]: The skill functions as a codebase navigation helper, utilizing standard tools like ripgrep (rg) and fd to find files and patterns.
[PROMPT_INJECTION]: The skill reads and processes local codebase content, which creates a surface for indirect prompt injection if the codebase contains malicious instructions.
Ingestion points: File content and names from the local repository.
Boundary markers: No delimiters defined to separate content from instructions.
Capability inventory: Search and read capabilities using rg, fd, and grep.
Sanitization: No explicit sanitization or filtering of codebase content is provided.

explorer