create-cowork-plugin
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use shell commands such as 'zip' and 'cp' to package the final plugin file and deliver it to the user's output directory.
- [COMMAND_EXECUTION]: It utilizes the 'claude plugin validate' CLI command to verify the structure and manifest of the newly created plugin.
- [SAFE]: The skill implements a controlled development process with specific validation steps and enforcement of safe naming conventions (kebab-case) to mitigate risks associated with automated file creation and command execution.
Audit Metadata