The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's execution logic utilizes shell commands like mkdir -p {destination_dir} and cp {source} {destination} where the variables are derived from user-provided plugin and command names. Without explicit validation or sanitization of these inputs, there is a risk that a malicious user could provide strings containing shell metacharacters to execute arbitrary commands.
[SAFE]: The skill operates exclusively on the local filesystem within standard configuration paths (.claude/ and ~/.claude/).
[SAFE]: No evidence of external network activity, hardcoded credentials, or remote code downloads was found in the provided file.

copy-command