📦
審計紀錄
interview-me - 2 審計
版本對比
各稽核版本間的能力與發現變化,最新在前。
審計版本 2 最新
2026年9月19日 下午12:31
All 24 static findings are false positives. The external-command matches are Markdown backticks, fenced examples, or prose, and the blocker matches describe interview guidance rather than system reconnaissance.
1
已掃描檔案
226
分析行數
1
複核項目
0
已忽略的誤報
風險因素
⚙️ 外部命令 (21)
SKILL.md:14 SKILL.md:36 SKILL.md:44-47 SKILL.md:47-57 SKILL.md:57-60 SKILL.md:60-98 SKILL.md:98-109 SKILL.md:109-138 SKILL.md:138-144 SKILL.md:144-146 SKILL.md:146-149 SKILL.md:149-153 SKILL.md:153-155 SKILL.md:155-176 SKILL.md:176-182 SKILL.md:182 SKILL.md:183 SKILL.md:184-185 SKILL.md:185-186 SKILL.md:186-225 SKILL.md:225
審計單位: codex
2026年8月30日 下午01:28
All 24 static findings are false positives caused by Markdown backticks and ordinary requirements language. No command execution or system reconnaissance capability was found. The interview method can bias user decisions through leading questions.
1
已掃描檔案
226
分析行數
2
複核項目
0
已忽略的誤報
已確認的安全問題 (1)
中
Leading Interview Guidance Can Bias Decisions
The skill directs agents to use leading questions and attach a hypothesis to each question. This can steer users toward the agent’s assumptions during high-impact decisions.
The instructions explicitly endorse leading questions and discuss user agreeableness. The effect is contextual rather than technical, so the finding is limited to undue influence risk.
風險因素
⚙️ 外部命令 (21)
SKILL.md:14 SKILL.md:36 SKILL.md:44-47 SKILL.md:47-57 SKILL.md:57-60 SKILL.md:60-98 SKILL.md:98-109 SKILL.md:109-138 SKILL.md:138-144 SKILL.md:144-146 SKILL.md:146-149 SKILL.md:149-153 SKILL.md:153-155 SKILL.md:155-176 SKILL.md:176-182 SKILL.md:182 SKILL.md:183 SKILL.md:184-185 SKILL.md:185-186 SKILL.md:186-225 SKILL.md:225
審計單位: claude