The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes npx skills commands to find and add packages. It specifically utilize the -y flag to skip confirmation prompts during installation, which increases risk if the agent is misled.
[EXTERNAL_DOWNLOADS]: The skill facilitates downloading code from GitHub and npm. It references trusted sources such as vercel-labs.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection via the processing of external search results.
Ingestion points: Descriptions and metadata returned by npx skills find (SKILL.md).
Boundary markers: None identified; the skill directly incorporates search results into its output.
Capability inventory: The skill can install new executable code and update existing tools via the npx skills add and npx skills update commands (SKILL.md).
Sanitization: The skill does not perform validation or sanitization of the external registry data.

find-skills