The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the npx skills CLI tool to perform operations such as searching (find), installing (add), and updating skills. It includes instructions to use the -y flag to skip confirmation prompts during installation.
[EXTERNAL_DOWNLOADS]: The skill is designed to download and install external code packages from the agent skills ecosystem. It references repositories from well-known sources like Vercel Labs to provide optimization guidelines and best practices.
[INDIRECT_PROMPT_INJECTION]: The skill interacts with external data that could potentially contain malicious instructions.
Ingestion points: User-provided search queries and the output returned by the npx skills find command (which includes repository names and descriptions from the external ecosystem).
Boundary markers: No specific delimiters or instructions are provided to the agent to ignore potentially malicious content within search results.
Capability inventory: The skill has the ability to install and execute code via the npx skills add command.
Sanitization: There is no evidence of validation or sanitization for the data retrieved from the search command before it is used to suggest or perform installations.

find-skills