wp-acf-and-content-modeling Rapport d’audit.

Avertissements

• Dependency or permission surface needs review
• Permission surface may require sandboxing
• Financial research output is not financial advice; require human review before any live investment decision
• Reference files are referenced via relative paths to a sibling claude-skills directory, but the submitted skill directory excerpt only includes SKILL.md; this can make the skill incomplete or broken when used outside the full repository.
• SKILL.md does not include setup, explicit input/output contract, or limitations/edge cases, so users must infer how the skill should be invoked and what its boundaries are.
• The skill instructs the agent to review and report findings, but there are no safety guardrails such as 'do not modify files' or 'do not execute commands'.
• Financial research output is not financial advice; require human review before any live investment decision.
• Quality score needs review
• Permission surface needs review: secrets or environment access, filesystem or document access
• GitHub adoption: 88 GitHub stars
• Stars/forks activity: 88 stars, 9 forks; issue activity unavailable in current metadata
• Dependency/runtime risk: credential or environment access, network or browser surface

Méthode

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.