The Agent Skills Directory

[REMOTE_CODE_EXECUTION] (HIGH): The skill uses npx skills add to download and execute code from arbitrary external GitHub repositories, presenting a significant remote code execution vector.
[EXTERNAL_DOWNLOADS] (HIGH): The documentation explicitly instructs the agent to use the -y and -g flags to auto-approve global installations. This removes the critical human-in-the-loop security check for third-party software installation.
[COMMAND_EXECUTION] (MEDIUM): The skill executes shell commands that can modify the system environment and persist through global package installations.
[PROMPT_INJECTION] (LOW): The skill is vulnerable to indirect prompt injection. Ingestion points: Data returned from search queries via npx skills find. Boundary markers: Absent; there are no instructions to isolate or ignore instructions that may be contained within the search results. Capability inventory: The agent has the capability to download and install third-party software. Sanitization: No validation is performed on the package names or repository sources before the agent offers to install them.

find-skills