skills/mitsuhiko/agent-commands/uv/Gen Agent Trust Hub

uv

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a documentation guide for 'uv', an industry-standard Python tool developed by Astral. The instructions reflect typical developer workflows for package management and script execution.\n- [EXTERNAL_DOWNLOADS]: The documentation references common and trusted Python libraries like 'requests', 'rich', and 'httpx' from public registries. It also outlines the legitimate use of alternative package indices via the '--index' flag for custom repository configurations.\n- [COMMAND_EXECUTION]: The skill explains how to execute Python scripts using 'uv run', covering various methods including local file execution, piped input from stdin, and scripts containing inline metadata or shebangs.\n- [PROMPT_INJECTION]: No evidence was found of prompt injection attempts, instructions to override agent safety guidelines, or deceptive metadata designed to misdirect the AI agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 10:53 PM