skills/zernie/vigiles/test-harness/Gen Agent Trust Hub

test-harness

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the vigiles package and the @anthropic-ai/claude-code CLI via standard Node.js package managers (npm, pnpm, yarn). The Anthropic CLI is recognized as an official tool from a well-known service provider.\n- [COMMAND_EXECUTION]: The skill provides instructions to execute shell commands to manage dependencies and run test suites (e.g., npx vigiles test, npx vigiles eval). These commands are standard for development workflows and transparently described.\n- [SAFE]: The skill promotes security best practices by describing a sandboxing mechanism ('bubblewrap') used during testing to restrict network egress and host file access when evaluating third-party or untrusted scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 10:28 PM
Security Audit — agent-trust-hub — test-harness