Skills
skills/wyattowalsh/agents/skill-quality-dashboard/Gen Agent Trust Hub

skill-quality-dashboard

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/check.py utilizes subprocess.run to execute local validation utilities and the internal aggregation script.
  • Evidence: subprocess.run calls in scripts/check.py invoke validate_skill.py, validate_evals.py, and aggregate_reports.py.
  • Context: The execution environment is restricted to local Python scripts with paths derived programmatically from the skill's own directory. No user-supplied arguments or untrusted inputs are interpolated into the command strings.
  • [SAFE]: The skill operates entirely within the local file system, specifically targeting the docs/public/generated-reports/ directory.
  • Evidence: scripts/aggregate_reports.py uses Path.glob to find and load local JSON files.
  • Context: There are no network operations, hardcoded credentials, or attempts to access sensitive system files (e.g., SSH keys or environment variables). Metadata and instructions in SKILL.md explicitly define the tool as a read-only dashboard.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 02:05 AM
Security Audit — agent-trust-hub — skill-quality-dashboard