evals-validate Audit report.

Warnings

• The skill executes external commands (npx, pytest) which could be risky if the project environment is compromised, but this is inherent to its purpose and not a critical flaw.
• No explicit security guidance is provided for running evaluations in untrusted environments.
• Quality score needs review
• Stars/forks activity: 132 stars, 1 forks; issue activity unavailable in current metadata

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.