uv
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides detailed workflows for executing shell commands and Python scripts using the
uvutility, includinguv run,uvx, anduv pipcommands. - [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and install third-party packages and CLI tools from external registries such as PyPI using
uv addanduvx. - [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection through the processing of untrusted project files.
- Ingestion points: The agent reads external files including
pyproject.toml,uv.lock, andrequirements.txtto manage dependencies. - Boundary markers: There are no explicit markers or instructions to treat data within these files as non-executable text or to ignore embedded instructions.
- Capability inventory: The skill is allowed to use
Bashfor command execution andWrite/Editfor file system modification. - Sanitization: No sanitization logic or validation is implemented for the content extracted from these external configuration files.
Audit Metadata