The Agent Skills Directory

[SAFE]: The skill is a technical reference for BoxLang file operations including reading, writing, and directory management. No malicious patterns, obfuscation, or unauthorized data access were detected.
[INDIRECT_PROMPT_INJECTION]: The skill describes processing external data sources (CSV, JSON, and file uploads) which inherently creates an attack surface for indirect prompt injection. However, the documentation proactively addresses this by providing 'Best Practices' and 'Security Patterns' sections that explicitly instruct the agent to use sanitization methods like getFileFromPath() and expandPath() to prevent path traversal and other injection attacks.
[COMMAND_EXECUTION]: The skill defines standard file-system commands (copy, move, delete). These are within the expected scope of a file-handling utility and are accompanied by safety recommendations for production use.

boxlang-file-handling