The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute a bundled Python script (file_stats.py) using relative paths and references configuration files in sibling directories (e.g., ../codeprobe/).\n- [PROMPT_INJECTION]: The skill processes untrusted code files from a target project, creating an indirect prompt injection surface.\n
Ingestion points: The skill uses Read, Grep, and Glob to process files in the user's project directory.\n
Boundary markers: There are no instructions to use delimiters or warnings to ignore embedded instructions within the analyzed files.\n
Capability inventory: The agent has access to Bash (command execution), Read (file access), and search tools (Grep, Glob).\n
Sanitization: No sanitization or validation of the ingested code content is performed before processing.

codeprobe-architecture