NYC

test-specialist

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOW
Full Analysis
  • [SAFE] (SAFE): The skill contains utility scripts for static analysis of test coverage. It does not perform network requests, access sensitive credentials, or execute arbitrary code from untrusted sources.
  • [DATA_EXPOSURE] (INFO): The scripts analyze_coverage.py and find_untested_code.py scan the local file system for source files and coverage reports. This is consistent with the skill's stated purpose as a 'test-specialist' and does not involve exfiltration of sensitive data.
  • [COMMAND_EXECUTION] (LOW): While the skill includes Python scripts intended for execution, the current entry point (index.js) is a placeholder and does not automatically spawn subprocesses. Any execution would be at the direction of the agent/user for development purposes.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 10:56 PM