The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs the agent on how to install and execute third-party packages using the npx skills add command. This represents a capability to download and run remote code. The skill includes specific verification steps (Step 4) to mitigate risk by prioritizing trusted organizations and highly-rated packages.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of search results from the npx skills find command. This data could contain malicious instructions designed to manipulate the agent's subsequent actions. The skill provides sanitization guidance by requiring the agent to validate the source reputation and installation metrics of the skills found.\n- [COMMAND_EXECUTION]: The skill utilizes the npx skills CLI for lifecycle management of other skills. It suggests using the -y flag during installation to bypass confirmation prompts, which allows for automated command execution while reducing direct user oversight of the installation process.

find-skills