The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Bash to execute system commands for checking file sizes and deleting application tracking data.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied arguments to determine deletion logic, which represents an attack surface for command injection if malicious inputs are interpolated into shell commands without validation.
Ingestion points: The skill parses $ARGUMENTS for cleanup flags and parameters in SKILL.md.
Boundary markers: No delimiters or warnings are used to separate user arguments from the instruction context.
Capability inventory: The skill uses the Bash tool to perform operations including du, find, wc, and file deletion (rm) within the ~/.claude-context-optimizer/ directory.
Sanitization: No explicit instructions are provided to sanitize, escape, or validate the $ARGUMENTS variable before it is used in system calls.

cco-clean