The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides an installation command (curl -fsSL https://vite.plus | bash) that downloads a script from an external domain and pipes it directly into the bash shell. This is a highly dangerous pattern as it executes unverified code with the privileges of the current user.
[COMMAND_EXECUTION]: The skill recommends several tools that require local command execution, including just, docker, and launchd. It specifically suggests configuring launchd for background task persistence on macOS.
[EXTERNAL_DOWNLOADS]: The skill directs users to download and install software from the domain vite.plus, which is not a recognized or well-known technical service or trusted organization repository.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: Technical selection tasks and tool recommendation requests in processed task descriptions. Boundary markers: Absent. Capability inventory: Remote code execution (curl | bash) and system command execution (just, docker). Sanitization: Absent. This surface could be exploited to influence the agent's technical recommendations or trigger malicious commands.

tech-preferences