ui-skills-root
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to interact with the environment using shell commands via the
ui-skillsCLI (e.g.,npx ui-skills start,npx ui-skills categories). - [EXTERNAL_DOWNLOADS]: The use of
npx ui-skillstriggers the download and execution of theui-skillspackage from the public NPM registry at runtime. The instructions do not specify a version, meaning the latest version is fetched dynamically. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to fetch external instructions and contexts via
npx ui-skills get <slug>and "load" them into the agent's current session. - Ingestion points: Content retrieved via the
getcommand in the CLI is integrated directly into the agent's active context (SKILL.md). - Boundary markers: There are no boundary markers or instructions to the agent to treat the fetched content as untrusted or to ignore embedded instructions within that content.
- Capability inventory: The skill is intended for use in environments like Claude Code and Cursor, which possess extensive capabilities including terminal command execution, file system modification, and network access.
- Sanitization: The skill does not perform or instruct any validation or sanitization of the remote content before it is processed by the agent.
Audit Metadata