المهارات vet

📦

vet

Name: vet
Author: imbue-ai

مراجعة المحتوى r1 مخاطر عالية ⚙️ الأوامر الخارجية📁 الوصول إلى نظام الملفات

使用 Vet 審查程式碼變更

程式碼變更可能偏離使用者請求，而測試也可能漏掉工作流程問題。Vet 會審查 git diff 和選用的 session history，讓代理能更早發現問題。

يدعم: Claude Codex Code(CC)

⚠️ 38 ضعيف

Maintain this Skill? Claim it ⚠️ 38 ضعيف

توقف واطلب التأكيد قبل التثبيت.

راجع الخطة واحصل على موافقة صريحة من المستخدم قبل تغيير الملفات.

التثبيت باستخدام Agent لدي

انسخ هذا الطلب إلى Agent لديك. يتضمن صفحة Skill المعتمدة وملف manifest.

طلب الوكيل

Review the Skillstore skill "vet" from https://skillstore.io/skills/imbue-ai-vet.md and its manifest at https://skillstore.io/api/skills/imbue-ai-vet/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

يجب أن يواصل Agent عرض خطته وطلب أي تأكيد تفرضه سياسة الأمان.

موارد مهيّأة لـ Agents

استخدم هذه الروابط عندما يحتاج AI Agent أو crawler أو script إلى سياق نظيف بدلًا من قراءة الصفحة كاملة.

تفاصيل Markdown GET /skills/imbue-ai-vet.md manifest موقَّع GET /api/skills/imbue-ai-vet/manifest lockfile موقَّع GET /api/skills/imbue-ai-vet/lockfile

اختبرها

جارٍ استخدام "vet". 一個小型重構變更了 authentication middleware 並更新測試。

النتيجة المتوقعة:

Vet 回報 middleware 現在略過了一個錯誤路徑。審查建議在合併前新增 expired tokens 的測試。

جارٍ استخدام "vet". 一個 Codex session 在多個檔案中實作了要求的 UI 變更。

النتيجة المتوقعة:

Vet 會比對對話請求與 diff，並指出 mobile spacing 尚未處理。它建議檢查 narrow viewport。

جارٍ استخدام "vet". 一個大型分支包含其他代理的工作和目前任務。

النتيجة المتوقعة:

Vet 會標記完整 diff 中的問題，並分離出看似與目前 session 無關、需由人工分流的項目。

التدقيق الأمني

مخاطر عالية

v4 • ٥‏/٧‏/٢٠٢٦ فتح التقرير المرتبط بالإصدار

The skill intentionally runs local vet commands and optional history-loader scripts that read assistant conversation files under hidden home directories. Many markdown backtick detections are false positives, but the documented command execution and transcript access are real privacy and execution risks. No prompt injection language or direct network exfiltration code was found in the reviewed files.

الملفات التي تم فحصها

269

الأسطر التي تم تحليلها

عناصر المراجعة

تم تجاهل الإيجابيات الكاذبة

مخاوف أمنية مؤكدة (3)

مرتفع

SKILL.md:10 SKILL.md:33-43 SKILL.md:55-62

Sensitive Conversation History Exposure

The skill is designed to review conversation history along with git diffs. The documented history loaders and session discovery steps can expose prompts, assistant replies, code, file paths, and secrets to vet processing.

The documentation explicitly says vet reviews conversation history and gives loader commands for OpenCode, Codex, and Claude Code. The listed hidden session paths are known places where sensitive transcripts are stored.

متوسط

SKILL.md:3 SKILL.md:8

Autonomous Tool Execution Pressure

The skill tells agents to run vet immediately after each logical unit of code changes and not wait to be asked. This can lead to unrequested command execution, especially when combined with history-loader guidance.

The instruction is repeated in the front matter and main text. It is not malicious by itself, but it creates consent risk for commands that inspect local data.

متوسط

scripts/export_opencode_session.py:8-12 scripts/export_opencode_session.py:32-34

Unvalidated Session Identifier Used in File Paths

The OpenCode exporter uses the supplied session id to build a filesystem path before validating the expected ses_ format. A malformed value could cause unintended directory traversal behavior in local file reads.

The path is directly derived from user input and message ids without visible normalization or validation. Exploitability is limited because the script expects OpenCode-shaped local JSON, so confidence is medium.

عناصر مراجعة القدرات (19)

هذه قدرات محلية حقيقية قد يُتوقع وجودها لهذه المهارة، لذا فهي تتطلب مراجعة ولكن لا تُحتسب كسلوك خبيث مؤكد.

مرتفع

SKILL.md:33

Hidden file in home directory

vet "goal" --history-loader "python ~/.agents/skills/vet/scripts/export_opencode_session.py --sessio

The OpenCode command runs a Python script from a hidden home directory path. It is part of the intended setup, but hidden home access is a real privacy and integrity risk.

مرتفع

SKILL.md:38

Hidden file in home directory

vet "goal" --history-loader "python ~/.codex/skills/vet/scripts/export_codex_session.py --session-fi

The Codex command references a hidden ~/.codex skill path and takes a session file. This can expose local assistant conversation history.

مرتفع

SKILL.md:43

Hidden file in home directory

vet "goal" --history-loader "python ~/.claude/skills/vet/scripts/export_claude_code_session.py --ses

The Claude Code command references a hidden ~/.claude skill path and a session file. This is intended but still sensitive hidden-home access.

مرتفع

SKILL.md:55

Hidden file in home directory

2. Run: `grep -rl "UNIQUE_MESSAGE" ~/.local/share/opencode/storage/part/` to find the matching part

The grep command searches ~/.local/share/opencode storage for conversation text. That directory can contain sensitive local session history.

مرتفع

SKILL.md:60

Hidden file in home directory

**Codex:** Session files are stored in `~/.codex/sessions/YYYY/MM/DD/`. Find the correct conversatio

The guidance directs users to inspect ~/.codex/sessions for the correct conversation. Codex session files can contain prompts, code, and secrets.

مرتفع

SKILL.md:62

Hidden file in home directory

**Claude Code:** Session files are stored in `~/.claude/projects/<encoded-path>/`. The encoded path

The guidance directs users to inspect ~/.claude/projects for conversation files. Those hidden files may contain sensitive project and prompt data.

متوسط

SKILL.md:16-25

Ruby/shell backtick execution

```bash

The fenced block instructs users to run pip, uv, and vet commands. Installing and executing a package is a real external command risk, even though the markdown fence itself is benign.

متوسط

SKILL.md:32-34

Ruby/shell backtick execution

```bash

The OpenCode example runs the vet CLI and a Python history-loader script. That is intentional external command execution with local data access.

متوسط

SKILL.md:37-39

Ruby/shell backtick execution

```bash

The Codex example runs vet with a Python history-loader script. This is external command execution that can process local session files.

متوسط

SKILL.md:42-44

Ruby/shell backtick execution

```bash

The Claude Code example runs vet with a Python history-loader script. This is a real external command path that can read local conversation history.

متوسط

SKILL.md:47-49

Ruby/shell backtick execution

```bash

The example instructs running the vet CLI. Even without history loading, it executes a local command over repository state.

متوسط

SKILL.md:55-57

Ruby/shell backtick execution

2. Run: `grep -rl "UNIQUE_MESSAGE" ~/.local/share/opencode/storage/part/` to find the matching part

The instruction uses grep over OpenCode storage to locate a session. This is external command execution against local application data.

متوسط

SKILL.md:77-78

Ruby/shell backtick execution

- `--agentic`: Mode that routes analysis through the locally installed Claude Code or Codex CLI inst

The --agentic option states that vet routes analysis through local Claude Code or Codex CLIs. That mode can invoke external local tools, although only when selected.

متوسط

SKILL.md:33

Hidden file access

vet "goal" --history-loader "python ~/.agents/skills/vet/scripts/export_opencode_session.py --sessio

The OpenCode example executes a loader from a hidden home directory. This hidden-file access is expected for the skill but should be consent-gated.

متوسط

SKILL.md:38

Hidden file access

vet "goal" --history-loader "python ~/.codex/skills/vet/scripts/export_codex_session.py --session-fi

The Codex example uses a hidden ~/.codex path and a session file. Access to that data is privacy-sensitive even when used for code review.

متوسط

SKILL.md:43

Hidden file access

vet "goal" --history-loader "python ~/.claude/skills/vet/scripts/export_claude_code_session.py --ses

The Claude Code example uses a hidden ~/.claude path and session file. The access is intentional but sensitive.

متوسط

SKILL.md:55

Hidden file access

2. Run: `grep -rl "UNIQUE_MESSAGE" ~/.local/share/opencode/storage/part/` to find the matching part

The command searches hidden OpenCode storage for a unique message. That is direct access to local conversation data.

متوسط

SKILL.md:60

Hidden file access

**Codex:** Session files are stored in `~/.codex/sessions/YYYY/MM/DD/`. Find the correct conversatio

The guidance instructs locating files under ~/.codex/sessions. This is hidden-file access to assistant transcripts.

متوسط

SKILL.md:62

Hidden file access

**Claude Code:** Session files are stored in `~/.claude/projects/<encoded-path>/`. The encoded path

The guidance instructs locating files under ~/.claude/projects. This is hidden-file access to assistant transcripts.

عوامل الخطر

⚙️ الأوامر الخارجية (22)

📁 الوصول إلى نظام الملفات (12)

SKILL.md:33 SKILL.md:38 SKILL.md:43 SKILL.md:55 SKILL.md:60 SKILL.md:62 SKILL.md:33 SKILL.md:38 SKILL.md:43 SKILL.md:55 SKILL.md:60 SKILL.md:62

دقّقه: codex عرض سجل التدقيق →

شارك واستشهد بهذا التقرير

شارك تقرير التقييم المرتبط بالإصدار والشارة المحايدة وبطاقة التضمين والاستشهادات. تعرض Skillstore الأدلة من دون أن تقرر ما إذا كانت هذه المهارة آمنة.

فتح التقرير المرتبط بالإصدار

نسخ رابط التقرير

https://skillstore.io/skills/imbue-ai-vet/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

شارة Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/imbue-ai-vet/security.svg)](https://skillstore.io/skills/imbue-ai-vet?utm_source=security_passport_badge)

شارة HTML

<a href="https://skillstore.io/skills/imbue-ai-vet?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/imbue-ai-vet/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

بطاقة قابلة للتضمين

<iframe src="https://skillstore.io/embed/skills/imbue-ai-vet.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

الاستشهادات الأكاديمية (APA · BibTeX · CFF)

اقتباس APA

imbue-ai. (2026). vet security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/imbue-ai-vet/audits/4

اقتباس BibTeX

@techreport{imbue-ai-imbue-ai-vet-2026,
  author = {imbue-ai},
  title = {vet security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/imbue-ai-vet/audits/4},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "vet security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "imbue-ai"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/imbue-ai-vet/audits/4"
identifiers:
  - type: other
    value: "skillstore:imbue-ai-vet:audit:4"
    description: "Skillstore immutable audit report identifier"

تقييم Skillstore

سبب هذا التقييم موثوقية الأدلة: متوسط

الهندسة المعمارية

قابلية الصيانة

المحتوى

المجتمع

الامتثال للمواصفات

ما الذي يمكنك بناؤه

檢查代理的程式碼變更

在每個聚焦的實作步驟後執行 vet，以捕捉遺漏需求或回歸風險。

根據意圖審查 Diff

將 conversation history 與 git diff 搭配使用，比對被要求的內容與實際變更。

標準化審查輸出

使用輸出和門檻選項，為 pull request 或本機審查建立一致的發現項目。

جرّب هذه الموجّهات

執行基本 Vet 審查

在不使用 conversation history 的情況下，對目前的 git diff 執行 vet。摘要任何問題，並說明是否仍需要測試。

使用 Session Context 審查

使用此對話正確的 session history 執行 vet。檢查實作是否符合使用者請求，並只列出可執行的問題。

調整審查嚴格度

使用選定的 base commit 和 confidence threshold 執行 vet。說明哪些發現是高信心，哪些需要人工判斷。

準備 Pull Request 發現項目

使用適合 pull request 的 output format 執行 vet。將結果轉換成精簡的審查摘要，包含風險、證據和建議修正。

أفضل الممارسات

在小型、邏輯性的變更後執行 vet，讓發現項目保持聚焦。
從隱藏目錄載入 conversation history 前，先徵求同意。
將 vet 視為額外審查層，接著執行專案測試。

تجنب

未經使用者核准，請勿在私人 sessions 上執行 history loaders。
不要只因變更來自另一個 session 就忽略發現項目。
不要使用 vet 結果取代編譯、測試或人工審查。

الأسئلة المتكررة

這個 skill 做什麼？

它會引導代理在程式碼變更後執行 vet CLI，並審查產生的發現項目。

它需要 conversation history 嗎？

不需要。Vet 可以不使用 history 執行，但 history 有助於比對實作與請求。

它支援哪些工具？

指示中包含 OpenCode、Codex 和 Claude Code session history 的範例。

它可以讀取敏感檔案嗎？

可以。History-loader workflows 可能會讀取隱藏的 session 目錄，其中可能包含敏感 prompts 和程式碼。

vet 可以取代測試嗎？

不能。此 skill 說明 vet 不能取代執行測試。

誰應該使用它？

它最適合想要頻繁審查 code diff 的開發者和代理操作者。

تفاصيل المطور

المؤلف

imbue-ai

الترخيص

MIT

مراجعة Skillstore

تنبيه الإصدار

لم يعلن المؤلف عن إصدار.

المستودع

https://github.com/imbue-ai/vet/tree/main/skills/vet

مرجع

30c73eac2afe762f6aa9c4553158769369d47351

حداثة الصيانة

٢٥‏/٧‏/٢٠٢٦

الاستخدام

4 تنزيلات · 104 مشاهدات

بنية الملفات

📁 scripts/

📄 export_claude_code_session.py

📄 export_codex_session.py

📄 export_opencode_session.py

📄 SKILL.md