The Agent Skills Directory

[SAFE]: The skill consists solely of documentation and instructional content. It does not contain any executable scripts, binaries, or command-line instructions that pose a direct security risk.- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for the agent to read and modify source code, which introduces an indirect prompt injection surface if the code being processed contains malicious instructions.- Ingestion points: The agent is instructed to read and analyze source code files to identify complexity patterns (SKILL.md).- Boundary markers: The skill does not provide specific delimiters or instructions to ignore potential commands embedded within the code comments or strings of the files being refactored.- Capability inventory: The agent is expected to utilize file-system tools to read existing code and write refactored versions back to the project.- Sanitization: No explicit sanitization or validation of the input source code is defined in the process.

code-simplification