The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill uses npx skills add to install modular packages that contain executable code and tools. This allows for the execution of third-party code from external sources like GitHub.
[EXTERNAL_DOWNLOADS]: The skill facilitates downloading software from the open agent skills ecosystem. It explicitly instructs the agent to use the -y flag to skip user confirmation during the installation process, which reduces oversight.
[COMMAND_EXECUTION]: The skill directs the agent to execute shell commands via the npx utility to manage and update skills.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes search results and package metadata from external sources to make installation decisions.
Ingestion points: Output from the npx skills find command in SKILL.md.
Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands in search results.
Capability inventory: The agent can execute shell commands, manage files, and install new software packages via npx.
Sanitization: The skill recommends manual verification of install counts and source reputation, such as preferring packages from well-known organizations.

find-skills