The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the npx skills CLI. This includes find, add, check, and update commands used to manage the agent's environment.
[REMOTE_CODE_EXECUTION]: The npx skills add <package> command downloads and installs external skill packages from GitHub or other sources. These packages are modular extensions that can contain executable scripts. The documentation specifically suggests using the -y flag to skip user confirmation prompts during this process.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes and presents data from an external ecosystem.
Ingestion points: Search results and package metadata returned by the npx skills find command.
Boundary markers: None identified; the agent is instructed to present the found skill name and description directly to the user.
Capability inventory: The agent has the ability to execute shell commands (npx skills add) which can lead to the installation of arbitrary code.
Sanitization: There are no instructions for validating or sanitizing the content of the search results before presenting them or acting upon them.

find-skills