監査履歴
prove-it-ran - 2 監査
バージョン比較
監査済みバージョン間の機能と検出結果の変化(新しい順)。
2026年10月22日 19:21
All six static findings are false positives: Markdown formatting, local verification commands, and reporting guidance do not establish malicious execution or reconnaissance. No evidence found of prompt injection, credential access, or data exfiltration in SKILL.md. The regression procedure temporarily changes source files, so users should preserve unrelated edits.
リスク要因
⚙️ 外部コマンド (4)
2026年10月17日 19:49
All six static findings are false positives involving Markdown formatting, scoped verification commands, or evidence-reporting instructions. No evidence found of prompt injection, credential collection, exfiltration, or malicious command execution. Temporary source changes require care, but the procedure explicitly limits their scope and requires restoration.