skills/edwinhu/workflows/dev-test/Gen Agent Trust Hub

dev-test

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides shell command templates for platform detection (uname -s, checking $XDG_SESSION_TYPE), test directory discovery (ls -d tests/), and identifying test frameworks through file inspection (grep on package.json, pyproject.toml, etc.). These are routine operations for an automated development assistant.
  • [DATA_EXPOSURE]: The skill instructions involve reading local project metadata files (e.g., package.json, Cargo.toml, meson.build) to determine project requirements. This access is scoped to the working directory and does not target sensitive system credentials or personal user data.
  • [REMOTE_CODE_EXECUTION]: The skill provides instructions for executing standard local test runners such as pytest, npm test, and cargo test. It does not include patterns for downloading and executing untrusted remote scripts (e.g., curl | bash).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 01:38 PM
Security Audit — agent-trust-hub — dev-test