Skills
Navigate
skills/podo/design-agent-skills/baseline-ui/Gen Agent Trust Hub

baseline-ui

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes shell commands designed to check for the presence of installation files in ~/.agents/skills/ and local project directories.
  • [EXTERNAL_DOWNLOADS]: The installation instructions fetch external code from the ibelick/ui-skills GitHub repository using the npx skills command.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes UI source code provided by the user, which presents an attack surface for indirect instructions.
  • Ingestion points: UI files processed via the /baseline-ui <file> command or general conversation context.
  • Boundary markers: The skill does not explicitly define delimiters to separate processed code from the agent's instructions.
  • Capability inventory: The skill environment allows shell command execution and file reading/writing for UI fixes.
  • Sanitization: There are no mentioned mechanisms for sanitizing or escaping the content of the files being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 05:01 AM