The Agent Skills Directory

EXTERNAL_DOWNLOADS (HIGH): The skill provides instructions for the agent to download and install external code packages from potentially untrusted sources using npx skills add <package>. This allows third-party code to be integrated into the agent's environment without prior verification.
REMOTE_CODE_EXECUTION (HIGH): The use of the -y flag in the command npx skills add <owner/repo@skill> -g -y explicitly bypasses confirmation prompts, leading to automated execution of remote scripts and package code on the host machine.
COMMAND_EXECUTION (MEDIUM): The skill requires the agent to execute shell commands (npx skills). The search query [query] is derived from user prompts and interpolated into a command line, which may lead to command injection if the underlying execution environment does not adequately sanitize shell metacharacters.
PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection (Category 8).
Ingestion points: Data enters the agent context through the output of npx skills find which fetches external package metadata.
Boundary markers: None present; the agent treats search results as instructional data for presentation to the user.
Capability inventory: The skill has the capability to write to the file system and execute code via the add and update commands.
Sanitization: There is no evidence of sanitization or validation of the search results before the agent processes them.

find-skills