Skills
skills/edwinhu/workflows/ds-review/Gen Agent Trust Hub

ds-review

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill frontmatter defines several PreToolUse and PostToolUse hooks that execute Python scripts (e.g., ds-pre-subagent-clear.py, phase-gate-guard.py) using uv run. These are used for operational safeguards and workflow state management.
  • [COMMAND_EXECUTION]: The SKILL.md file employs dynamic context injection (the ! command syntax) to execute a local Python script (load-constraints.py) at load time to initialize project-specific constraints.
  • [REMOTE_CODE_EXECUTION]: The skill includes instructions and Python code templates for agents to execute 'Independent Verification' checks on analysis data. This runtime code execution is a documented and intended feature of the data science methodology review process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 06:30 AM
Security Audit — agent-trust-hub — ds-review