case-review
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseEvidence Graph Review
证据图谱审查
Use this skill when a reverse engineering, forensics, CTF, or authorized security case needs a defensible handoff. It audits the existing package without changing the case or touching a target.
work/<case>/当逆向工程、取证、CTF或授权安全案例需要可辩护的交付时,使用此技能。它会审计现有的包,不会修改案例或接触目标。
work/<case>/Scope
范围
This skill covers:
- Scope metadata and target-activity readiness
- Evidence record structure and reproducibility fields
- References from work items and timeline entries to Evidence
- Structured Findings and Paths in report Markdown
- Optional SHA-256 verification for case-local artifacts
- A Markdown or JSON review result for a report handoff
It MUST NOT perform reconnaissance, exploitation, dynamic instrumentation, or target changes. Those actions belong to the routed analysis skill and require the case scope gate.
本技能涵盖:
- 范围元数据和目标活动就绪情况
- 证据记录结构和可复现性字段
- 工作项和时间线条目到证据的引用
- 报告Markdown中的结构化结论(Findings)和路径(Paths)
- 案例本地工件的可选SHA-256验证
- 用于报告交付的Markdown或JSON审查结果
禁止执行侦察、利用、动态插装或修改目标的操作。这些操作属于路由分析技能,需要案例范围准入。
ACTION REQUIRED
必须执行的操作
- : read
NOWand confirm that this is a review of an existing authorized case package.../field-journal/precedent-reverse.md - : confirm the case path and choose read-only review mode.
NOW - : read
NEXT; this skill uses only Python 3 standard library and does not require bootstrap.../tool-index.md - : run
NEXT.python3 scripts/review_case.py <case-root> --format markdown - : resolve every error, then rerun the review before claiming a handoff is complete.
ACT
- :阅读
立即,确认本次审查针对的是已授权的现有案例包。../field-journal/precedent-reverse.md - :确认案例路径并选择只读审查模式。
立即 - :阅读
下一步;本技能仅使用Python 3标准库,无需引导安装。../tool-index.md - :运行
下一步。python3 scripts/review_case.py <case-root> --format markdown - :解决所有错误,然后重新运行审查,再确认交付完成。
执行
Tool dependencies
工具依赖
| Tool | Required | Purpose | Auto-bootstrap |
|---|---|---|---|
| Python 3.9+ | Yes | Runs the read-only case review script | No, use the platform Python installation |
No network access or third-party package is required.
| 工具 | 是否必需 | 用途 | 自动引导安装 |
|---|---|---|---|
| Python 3.9+ | 是 | 运行只读案例审查脚本 | 否,使用平台自带的Python安装版本 |
无需网络访问或第三方包。
Workflow
工作流程
Phase 1: Intake
阶段1:接收
Run the review against the existing case directory:
bash
python3 skills/case-review/scripts/review_case.py work/<case> --format markdownConfirm that , , , and are present. A non-strict review reports scope warnings while a strict review treats warnings as handoff blockers.
scope.mdtimeline.mdworkitems.mdevidence/针对现有案例目录运行审查:
bash
python3 skills/case-review/scripts/review_case.py work/<case> --format markdown确认、、和已存在。非严格审查会报告范围警告,而严格审查会将警告视为交付障碍。
scope.mdtimeline.mdworkitems.mdevidence/建议下一步(选一个编号)
建议下一步(选一个编号)
- 修复 scope.md 中的授权、范围或 network_profile 字段
- 继续检查 Evidence 记录的可复现命令和来源
- 导出当前 review 结果并附到阶段性报告
- 换 JSON 输出接入 CI 或其他审查工具
- 暂停,先确认审查范围
- 修复 scope.md 中的授权、范围或 network_profile 字段
- 继续检查 Evidence 记录的可复现命令和来源
- 导出当前 review 结果并附到阶段性报告
- 换 JSON 输出接入 CI 或其他审查工具
- 暂停,先确认审查范围
Phase 2: Traceability
阶段2:可追溯性审查
Review the checks for:
- Evidence IDs that do not exist
- Findings without
evidence_ids - Paths without an allowed or Evidence reference
path_type - Work items and timeline entries pointing to unknown Evidence
- Unlinked Evidence records
- Validated Findings with low confidence
An offline observation may use only when its field explicitly documents the offline limitation.
repro_command: n/anotesUse JSON when another tool needs stable fields:
bash
python3 skills/case-review/scripts/review_case.py work/<case> --format json检查以下内容:
- 不存在的证据ID
- 未关联的结论(Findings)
evidence_ids - 未包含合法或证据引用的路径(Paths)
path_type - 指向未知证据的工作项和时间线条目
- 未关联的证据记录
- 置信度低的已验证结论(Findings)
仅当字段明确记录离线限制时,离线观测才可使用。
notesrepro_command: n/a当其他工具需要稳定字段时,使用JSON格式:
bash
python3 skills/case-review/scripts/review_case.py work/<case> --format json建议下一步(选一个编号)
建议下一步(选一个编号)
- 补写缺失的 Evidence,并保留原始命令
- 将候选 Finding 绑定到 Evidence 后重新审查
- 为调用链或攻击链补充 P-id 和 Path 步骤
- 生成 Markdown handoff summary
- 换回 PRIMARY skill 继续分析
- 补写缺失的 Evidence,并保留原始命令
- 将候选 Finding 绑定到 Evidence 后重新审查
- 为调用链或攻击链补充 P-id 和 Path 步骤
- 生成 Markdown handoff summary
- 换回 PRIMARY skill 继续分析
Phase 3: Fixity verification
阶段3:完整性验证
When an Evidence record contains both and , verify the case-local artifact:
content_hashartifact_pathbash
python3 skills/case-review/scripts/review_case.py work/<case> --verify-hashes --strictThe script accepts and checks that the artifact remains inside the case root. A hash mismatch is a hard failure.
sha256:<64 hex characters>The PowerShell Evidence helper can record a hash while appending a record:
powershell
powershell -File skills/scripts/append-evidence.ps1 -CaseRoot work\<case> -Id E-001 -Title "Sample hash" -ReproCommand "sha256sum evidence/sample.bin" -ArtifactPath "evidence\sample.bin"当证据记录同时包含和时,验证案例本地工件:
content_hashartifact_pathbash
python3 skills/case-review/scripts/review_case.py work/<case> --verify-hashes --strict脚本接受格式,并检查工件是否仍在案例根目录内。哈希不匹配属于严重失败。
sha256:<64 hex characters>PowerShell证据助手可在添加记录时同时记录哈希:
powershell
powershell -File skills/scripts/append-evidence.ps1 -CaseRoot work\<case> -Id E-001 -Title "Sample hash" -ReproCommand "sha256sum evidence/sample.bin" -ArtifactPath "evidence\sample.bin"建议下一步(选一个编号)
建议下一步(选一个编号)
- 修复 hash mismatch 或替换已污染的工作副本
- 为未固定的原始文件补充 SHA-256 和 artifact_path
- 继续进入报告生成阶段
- 导出 JSON 结果供 CI 保存
- 暂停并请求人工复核
- 修复 hash mismatch 或替换已污染的工作副本
- 为未固定的原始文件补充 SHA-256 和 artifact_path
- 继续进入报告生成阶段
- 导出 JSON 结果供 CI 保存
- 暂停并请求人工复核
Phase 4: Handoff
阶段4:交付
Use strict mode before a final report or specialist handoff:
bash
python3 skills/case-review/scripts/review_case.py work/<case> --strict --format markdown > work/<case>/report/case-review.mdThe command is read-only with respect to the case unless shell redirection is explicitly used to save its output. The review is not legal advice and does not replace organizational evidence handling procedures.
在最终报告或专家交付前使用严格模式:
bash
python3 skills/case-review/scripts/review_case.py work/<case> --strict --format markdown > work/<case>/report/case-review.md除非明确使用shell重定向保存输出,否则该命令对案例是只读的。本审查不构成法律建议,也不能替代组织的证据处理流程。
建议下一步(选一个编号)
建议下一步(选一个编号)
- 将通过的 review 结果交给 生成正式报告
docs-generator/ - 回到 PRIMARY skill 补齐新的分析证据
- 归档 Markdown 和 JSON review 结果
- 暂停并请求人工复核
- 将通过的 review 结果交给 生成正式报告
docs-generator/ - 回到 PRIMARY skill 补齐新的分析证据
- 归档 Markdown 和 JSON review 结果
- 暂停并请求人工复核
Language behavior contract
语言行为约定
- Internal reasoning, tool selection, and phase control: English.
- User-visible messages, section labels, reports, and next-step menus: Chinese unless the user requests another language.
- Default bilingual labels place Chinese first and English second, separated by .
/
- 内部推理、工具选择和阶段控制:使用英文。
- 用户可见的消息、章节标签、报告和下一步菜单:默认使用中文,除非用户要求其他语言。
- 默认双语标签以中文在前、英文在后,用分隔。
/
Bootstrap boundary
引导安装边界
This skill has no third-party dependency. If Python 3 is unavailable, the only allowed recovery action is the repository bootstrap path when a Python capability is registered for the current platform. If no such capability is registered, stop and report the missing runtime. Do not guess executable paths, download packages, or perform a manual install from inside this skill.
本技能无第三方依赖。如果Python 3不可用,唯一允许的恢复操作是当当前平台已注册Python能力时,使用仓库引导路径。如果未注册此类能力,请停止并报告缺失的运行时。请勿在本技能内猜测可执行路径、下载包或手动安装。
Routing context
路由上下文
Upstream entry: any reverse, forensics, CTF, or authorized security skill that has produced a case package.
Downstream exit: for a formal report, or the original PRIMARY skill when the graph is incomplete.
docs-generator/Related modules: , , , , and .
ops/evidence-finding-path.mdops/timeline-workitem.mddigital-forensics/reverse-engineering/docs-generator/上游入口:任何已生成案例包的逆向、取证、CTF或授权安全技能。
下游出口:用于生成正式报告的,或当图谱不完整时返回原始PRIMARY技能。
docs-generator/相关模块:、、、和。
ops/evidence-finding-path.mdops/timeline-workitem.mddigital-forensics/reverse-engineering/docs-generator/References
参考资料
任务完成自检
任务完成自检
- 我是否审查了 scope.md、timeline.md、workitems.md 和 evidence/?
- 所有 Finding 是否引用了现存 Evidence?
- 所有 Path 是否包含合法 path_type 和 Evidence 引用?
- 是否执行了 hash verification,或记录了未执行原因?
- 是否以 strict 模式重新运行并保存了 review 结果?
- 我是否审查了 scope.md、timeline.md、workitems.md 和 evidence/?
- 所有 Finding 是否引用了现存 Evidence?
- 所有 Path 是否包含合法 path_type 和 Evidence 引用?
- 是否执行了 hash verification,或记录了未执行原因?
- 是否以 strict 模式重新运行并保存了 review 结果?