iterative-retrieval 审计报告.

警告

• Permission surface may require sandboxing
• The skill is a conceptual pattern rather than a ready-to-use implementation; agents must adapt it to their environment.
• The SKILL.md lacks explicit setup instructions or integration guidance for different agent frameworks.
• The scoring criteria and thresholds (e.g., relevance >= 0.8) are subjective and may need tuning per use case.
• Quality score needs review
• Permission surface needs review: secrets or environment access, filesystem or document access
• GitHub adoption: 91 GitHub stars
• Stars/forks activity: 91 stars, 23 forks; issue activity unavailable in current metadata
• Permission surface: secrets or environment access, filesystem or document access

方法

本报告综合公开元数据、AI 审查输出、仓库活跃度、安装就绪度、OpenAgentSkill 事件、质量评分、信任检查和 Agent 安全门槛；它不是完整的源代码安全审计。