skills/abpai/skills/harness/Gen Agent Trust Hub

harness

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs extensive local repository analysis using common development tools. It executes commands such as git, ls, rg (ripgrep), and cat to inventory files, check repository state, and discover validation signals like package scripts or CI jobs.
  • [EXTERNAL_DOWNLOADS]: The skill fetches the @andypai/harness-doctor package from the NPM registry. This package provides the deterministic auditing rules used to score repository readiness and is identified as a vendor-owned resource associated with the author.
  • [REMOTE_CODE_EXECUTION]: The skill invokes the harness-doctor CLI using npx @andypai/harness-doctor@latest. This pattern executes code from the public NPM registry to perform automated audits. The skill includes an execution policy that advises users to confirm the resolved version before running and warns against executing production-mutating commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 09:07 PM
Security Audit — agent-trust-hub — harness