git-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to search for and report "敏感信息" and to populate "Commit 风险明细" in process.md/security_report.html without any redaction rules, which invites including secret values verbatim in generated output.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). 该技能流程在步骤3-4会读取用户仓库中的 git 提交元数据与变更内容（写入 process.md），随后 assets/vigil_report.py 在步骤6读取该 process.md 并将其中的作者/提交/文件范围/风险文本渲染进离线 HTML，从而让外部提交作者可通过其提交内容进入 LLM 运行时可读文本链路。