core Audit report.

Warnings

• The core skill intentionally has no standalone workflow; if installed without its sibling qa-skills skills, it is a passive library and may be confusing to an agent that tries to trigger it.
• The referenced scripts/*.py are not visible in the provided excerpt; their runtime behavior, file access, and input/output contracts should be reviewed before allowing agent execution.
• SKILL.md does not give a concrete consumption example (e.g., which relative path a dependent skill should reference and how the shared documents should be loaded), so integration is described but not demonstrated.
• Low GitHub adoption signal
• Quality score needs review
• GitHub adoption: 12 GitHub stars
• Stars/forks activity: 12 stars, 0 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.