The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard command-line utilities such as find, wc, grep, and awk to perform structural analysis of code files (e.g., counting lines, identifying function definitions, and detecting duplication). These operations are restricted to the local file system and are used solely for the skill's stated purpose of code refactoring analysis.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes user-provided source code.
Ingestion points: Reads files and directories specified by the user through the $TARGET variable in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious instructions embedded in the code comments of the files being analyzed.
Capability inventory: The skill uses find, wc, grep, awk, and echo to inspect file metadata and content.
Sanitization: No specific sanitization or filtering of the code content is implemented before analysis. However, given the read-only nature of the analysis tools, the impact is minimal.

refactor