attack-surface 監査レポート.

警告

• Permission surface may require sandboxing
• SKILL.md does not include an explicit authorization/scope guardrail; it assumes an engagement is already authorized but does not instruct the agent to verify scope boundaries.
• Phase 3 depends on a `check-exploit` skill that is not bundled or described, so the workflow may be incomplete if that skill is unavailable.
• Phase 1 provides categories but no concrete read-only enumeration tooling or commands, making output quality dependent on the model's prior knowledge.
• Low GitHub adoption signal
• Quality score needs review
• Permission surface needs review: secrets or environment access, filesystem or document access
• GitHub adoption: 36 GitHub stars
• Stars/forks activity: 36 stars, 9 forks; issue activity unavailable in current metadata
• Permission surface: secrets or environment access, filesystem or document access

方法

このレポートは公開メタデータ、AI レビュー、リポジトリの鮮度、インストール準備、OpenAgentSkill イベント、品質スコア、信頼チェック、Agent セーフティゲートを統合します。完全なソースコード監査ではありません。