uv-package-manager

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill provides commands for installing Python packages via uv add and uv sync. While this involves downloading external code, it is the primary and intended purpose of a package manager skill. The examples provided use well-known, legitimate packages like 'requests', 'fastapi', and 'pytest'.
  • [COMMAND_EXECUTION] (SAFE): The skill includes instructions for uv run, which executes local Python scripts or installed tools. This is a standard and necessary function for a development tool skill.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill has an attack surface for indirect prompt injection as it processes external files such as pyproject.toml, requirements.txt, and Git repositories.
  • Ingestion points: SKILL.md (via instructions to process pyproject.toml and requirements.txt).
  • Boundary markers: Absent in the instructions; the skill relies on the agent's default processing of these file types.
  • Capability inventory: Includes subprocess execution (uv run), package installation (uv add), and network operations (uv sync).
  • Sanitization: Relies on the underlying uv tool's verification of package integrity and lock files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM