The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides instructions for the agent to install and execute code from arbitrary remote GitHub repositories using the npx skills add <owner/repo@skill> command.
[COMMAND_EXECUTION]: Recommends the use of the -y flag in the installation command npx skills add <package> -g -y, which bypasses user confirmation prompts and human review before code is executed on the system.
[COMMAND_EXECUTION]: Suggests global installation of skills using the -g flag, which increases the potential system-wide impact of any installed code.
[EXTERNAL_DOWNLOADS]: Encourages downloading and running content from various unverified external sources identified through the search command, including non-trusted repositories.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). Ingestion points: Results from npx skills find [query] (SKILL.md). Boundary markers: None present to distinguish search results from system instructions. Capability inventory: npx skills add and npx skills update (RCE) in SKILL.md. Sanitization: None present to validate the safety of returned skill names or repositories.

find-skills