The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a bundled Node.js script (create-template-skill.mjs) to automate the generation of template packages. This execution uses a verified Node binary provided by the runtime environment and operates solely on local, user-provided files within defined directories. This is a standard functional requirement for the skill's purpose.
[REMOTE_CODE_EXECUTION]: The skill uses specific Node.js modules (fs, path, crypto, zlib) for local file manipulation and verification. It does not download or execute scripts from remote or untrusted servers. All dependencies are standard Node.js built-ins.
[DATA_EXFILTRATION]: There are no network operations or external URL requests detected in the skill or its supporting scripts. Data processing is confined to the local ~/.open-cowork directory.
[CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or secrets were found in the instructions, manifest, or scripts. The skill manages personal templates without requiring or storing authentication tokens.
[PROMPT_INJECTION]: The instructions in SKILL.md are descriptive and provide clear routing for the agent. They do not contain any patterns intended to bypass safety filters or override system-level instructions.

template-creator