python-project-workflow

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill defines a process for creating temporary Python verification scripts in the /tmp directory to validate changes during the project workflow.
  • [INDIRECT_PROMPT_INJECTION]: Ingestion points: The skill orientates itself by reading external files such as README.md, CI workflows, and pyproject.toml as defined in the Orientation Checklist of SKILL.md. Boundary markers: Absent. Capability inventory: The skill can write to files (references/safe-editing.md) and execute shell commands (references/lint-format-typing-testing.md). Sanitization: There is no explicit instruction to sanitize or escape data ingested from these files before processing.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of Python packages from the official PyPI registry via tools like pip and uv, which is standard for dependency management.
  • [COMMAND_EXECUTION]: The skill uses various shell commands for project tasks, including environment synchronization (uv sync), linting (ruff), and testing (pytest).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 11:48 AM
Security Audit — agent-trust-hub — python-project-workflow