test-guardian

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for manual diagnostic purposes and does not contain automated hooks or background processes.- [COMMAND_EXECUTION]: Provides standard command-line invocations for test runners and shell utilities (e.g., grep, find, awk) to identify performance bottlenecks and architectural issues in test suites. These commands operate within the local project scope.- [REMOTE_CODE_EXECUTION]: Uses bunx to run established testing frameworks. This is a standard development practice and does not involve executing arbitrary or untrusted remote scripts.- [DATA_EXPOSURE]: No hardcoded secrets, sensitive file paths, or network exfiltration patterns were identified. The skill's data operations are limited to reading local code for diagnostic patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 11:31 PM