uv-package-management

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing Python packages and CLI tools from external registries using uv add, uv tool install, and uv pip install.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute commands and Python scripts using uv run and uvx, facilitating local execution as part of its package management workflow.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection. 1. Ingestion points: External data enters the context via Python script files (SKILL.md) and package metadata during installation. 2. Boundary markers: No delimiters or instructions to ignore embedded commands are present when processing external content. 3. Capability inventory: Extensive capabilities including subprocess execution and file system modification via the uv toolset across all sections of SKILL.md. 4. Sanitization: No sanitization of external package names or script content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 04:17 AM