The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes Python scripts (scripts/auto-update.py and scripts/analyze_commands.py) to maintain its command index. These scripts are executed via subprocess.run, performing local file system operations to scan and parse documentation.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes and displays content from various markdown files in the project's .claude directory. Malicious content within these files could potentially influence agent behavior when the help system is used.
Ingestion points: Markdown files located in the commands/, agents/, and skills/ directories.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: The skill utilizes Read, Grep, and Glob tools to access files, and provides command orchestration features (Mode 5).
Sanitization: Content is extracted from frontmatter and file bodies without visible sanitization or validation against structural schemas.

ccw-help