uv-workflow
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute Python commands and scripts using
uv run. This is the core functionality and is used to manage environments and dependencies safely. - [EXTERNAL_DOWNLOADS]: The skill uses
uvto manage Python packages, which involves downloading dependencies from standard repositories like PyPI. This is documented for routine developer tasks such as running tests or scripts. - [PROMPT_INJECTION]: The skill defines a surface for processing user-provided Python tasks.
- Ingestion points: The skill accepts tasks via the
argument-hintinSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are present in the provided templates.
- Capability inventory: The skill utilizes
uv runto execute code, which involves subprocess calls (documented inSKILL.mdandreferences/uv-command-patterns.md). - Sanitization: No explicit sanitization or validation of the user-provided code is mentioned.
Audit Metadata