The Agent Skills Directory

[SAFE]: The skill's primary function is meta-programming—generating skeletons and boilerplate for other skills. It uses allowed tools such as Bash, Write, and AskUserQuestion to facilitate this process in a transparent and documented manner.
[COMMAND_EXECUTION]: Uses the Bash tool for legitimate file system operations such as directory creation (mkdir -p) within the workspace. These operations are scoped to the intended purpose of generating new skill packages.
[PROMPT_INJECTION]: No evidence of instructions designed to bypass safety filters, extract system prompts, or override agent constraints was found. The instructions focus on the logic and structure of the skill generation process.
[DATA_EXFILTRATION]: No sensitive file paths (e.g., SSH keys, credentials) are accessed, and no unauthorized network operations or exfiltration patterns were detected.
[REMOTE_CODE_EXECUTION]: The skill does not perform any remote code downloads or execute scripts from unverified external sources. It provides templates for local Python and Bash scripts that the user can later populate.

skill-generator