📦

skill-doctor

Name: skill-doctor
Author: warpdotdev

Ревизия содержимого r1 Высокий риск ⚙️ Внешние команды📁 Доступ к файловой системе🔑 Переменные окружения🌐 Доступ к сети⚡ Содержит скрипты

Grade and Improve Your Agent Skills

Agent skills are difficult to evaluate from configuration alone. This skill reviews local conversations, scores outcomes, and drafts evidence-based improvements.

Поддерживает: Claude Codex Code(CC)

⚠️ 38 Плохо

Остановитесь и запросите подтверждение перед установкой.

Проверьте план и получите явное согласие пользователя перед изменением файлов.

Установить с помощью моего Агента

Скопируйте этот запрос в своего Агента. Он содержит каноническую страницу Skill и манифест.

Запрос агента

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

Ваш Агент по-прежнему должен показать план и запросить все подтверждения, требуемые политикой безопасности.

Ресурсы для AI-агентов

Используйте эти ссылки, когда AI-агенту, crawler или script нужен чистый контекст вместо полной страницы.

Markdown-детали GET /skills/warpdotdev-skill-doctor.md Подписанный manifest GET /api/skills/warpdotdev-skill-doctor/manifest Подписанный lockfile GET /api/skills/warpdotdev-skill-doctor/lockfile

Протестировать

Использование «skill-doctor». Grade conversations in this repository from the last 30 days.

Ожидаемый результат:

Overall grade: B. The report highlights repeated verification delays, weak skill coverage, and one recurring code-quality defect.

Использование «skill-doctor». Evaluate project skills only and draft justified improvements.

Ожидаемый результат:

Three project skills were detected.
One description change is proposed from two failed sessions.
No installed skill files were modified.

Использование «skill-doctor». Review all supported local conversation sources.

Ожидаемый результат:

A combined local report summarizes sampled sessions, skill usage, scorer results, proposed edits, and a shareable image.

Аудит безопасности

Высокий риск

v1 • 28.08.2026 Открыть версионный отчет

Most static matches are false positives from Markdown formatting, test fixtures, CSS, or fixed-argument git subprocesses. Confirmed capabilities include reading Claude and Codex history directories and Warp conversation databases. Semantic review found prompt-injection and scope-enforcement gaps, unredacted transcript copies, and an unvalidated report link.

Просканировано файлов

2,906

Проанализировано строк

Пункты проверки

Ложные срабатывания проигнорированы

Подтверждённые проблемы безопасности (7)

Высокий

SKILL.md:92-97 SKILL.md:118-121 scripts/collect_sessions.py:304-332

Untrusted Transcript and Skill Content Enters Agent Context

The workflow asks the agent to read historical transcripts and installed skill files without a clear untrusted-data boundary. The narrow tag filter does not cover ordinary prompt-injection prose or tool outputs.

The skill explicitly loads transcript and skill text into the scoring workflow, while the collector filters only a short list of tag-shaped prefixes.

Высокий

SKILL.md:31-42 scripts/collect_sessions.py:935-944 scripts/collect_sessions.py:969-978

Conversation Scope Is Enforced After Content Parsing

For Claude Code and Codex, the collector parses each recent session before checking whether its working directory matches the selected projects. This reads out-of-scope conversation content into memory.

The control flow calls each full session parser before the repository-scope condition, directly contradicting the user-selected project boundary.

Средний

scripts/collect_sessions.py:519

SQLite database file

candidates.append(root / "warp.sqlite")

The collector discovers local Warp SQLite databases and later queries conversation records. Connections are read-only, but the records can contain sensitive conversation content.

Средний

scripts/collect_sessions.py:521

SQLite database file

candidates.extend(root.glob("*/warp.sqlite"))

The collector discovers local Warp SQLite databases and later queries conversation records. Connections are read-only, but the records can contain sensitive conversation content.

Средний

SKILL.md:53-56 scripts/collect_sessions.py:308-332 scripts/collect_sessions.py:1087-1090

Transcript Copies Lack Secret Redaction and Cleanup

The collector copies user messages, tool arguments, and tool outputs into persistent Markdown files. It truncates content but does not redact credentials or remove the scratch directory after use.

The source visibly writes condensed transcript fields to disk and contains no redaction or cleanup step.

Средний

scripts/render_report.py:308

Report Link Scheme Is Not Validated

The renderer escapes cta_url for HTML but accepts any URI scheme. A crafted report can place a javascript or data URL behind the visible Request access link.

HTML escaping does not restrict URI schemes, and the value is read directly from report data before insertion into href.

Низкий

assets/pierre-diffs.js:1

Unscanned file (too_large) — manual review required

[unscanned: too_large]

Force-confirmed metadata/low static finding; AI false-positive verdict rejected.

Пункты проверки возможностей (4)

Это реальные локальные возможности, которые могут ожидаться для этого навыка, поэтому они требуют проверки, но не считаются подтверждённым вредоносным поведением.

Высокий

scripts/collect_sessions.py:48

Hidden file in home directory

default=os.environ.get("CLAUDE_CONFIG_DIR", "~/.claude"),

This default is later used to enumerate Claude Code project-history files under the user home. Those histories can contain private prompts, outputs, and tool data.

Высокий

scripts/collect_sessions.py:51

Hidden file in home directory

p.add_argument("--codex-home", default=os.environ.get("CODEX_HOME", "~/.codex"))

This default is later used to enumerate Codex rollout files under the user home. Those histories can contain private prompts, outputs, and tool data.

Средний

scripts/collect_sessions.py:48

Hidden file access

default=os.environ.get("CLAUDE_CONFIG_DIR", "~/.claude"),

This default is later used to enumerate Claude Code project-history files under the user home. Those histories can contain private prompts, outputs, and tool data.

Средний

scripts/collect_sessions.py:51

Hidden file access

p.add_argument("--codex-home", default=os.environ.get("CODEX_HOME", "~/.codex"))

This default is later used to enumerate Codex rollout files under the user home. Those histories can contain private prompts, outputs, and tool data.

Факторы риска

⚙️ Внешние команды (50)

scripts/collect_sessions.py:90 scripts/collect_sessions.py:857 scripts/render_report.py:103 scripts/test_render_report.py:48 scripts/test_render_report.py:49 scripts/test_render_report.py:50 scripts/test_render_report.py:215 scripts/test_render_report.py:219 scripts/test_render_report.py:223-224 scripts/test_render_report.py:232 scripts/warp_decoder.py:4 scripts/warp_decoder.py:136 scripts/warp_decoder.py:286 scripts/warp_decoder.py:377 SKILL.md:13 SKILL.md:19 SKILL.md:25-27 SKILL.md:27-53 SKILL.md:53-55 SKILL.md:55-57 SKILL.md:57-62 SKILL.md:62-63 SKILL.md:63-64 SKILL.md:64-65 SKILL.md:65-66 SKILL.md:66-68 SKILL.md:68-73 SKILL.md:73-75 SKILL.md:75 SKILL.md:79-80 SKILL.md:80-81 SKILL.md:81-82 SKILL.md:82-83 SKILL.md:83-84 SKILL.md:84-85 SKILL.md:85-86 SKILL.md:86-88 SKILL.md:88 SKILL.md:94-95 SKILL.md:95-97 SKILL.md:97 SKILL.md:101-102 SKILL.md:102 SKILL.md:103-104 SKILL.md:104-105 SKILL.md:105-106 SKILL.md:106 SKILL.md:107-109 SKILL.md:109 SKILL.md:113-114

📁 Доступ к файловой системе (23)

🔑 Переменные окружения (6)

scripts/collect_sessions.py:48 scripts/collect_sessions.py:51 scripts/collect_sessions.py:60 scripts/collect_sessions.py:510 scripts/collect_sessions.py:512 scripts/collect_sessions.py:513

🌐 Доступ к сети (3)

scripts/render_report.py:308 scripts/test_render_report.py:104 SKILL.md:152

⚡ Содержит скрипты (2)

scripts/test_collect_sessions.py:11-17 scripts/test_render_report.py:8-14

Аудитор:: codex

Поделиться и цитировать этот отчет

Делитесь версионным отчетом об оценке, нейтральным значком, встраиваемой карточкой и цитатами. Skillstore публикует доказательства, не решая, безопасен ли этот Skill.

Открыть версионный отчет

Копировать ссылку на отчёт

https://skillstore.io/skills/warpdotdev-skill-doctor/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Значок Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/warpdotdev-skill-doctor/security.svg)](https://skillstore.io/skills/warpdotdev-skill-doctor?utm_source=security_passport_badge)

Значок HTML

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

Встраиваемая карточка

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

Академические ссылки (APA · BibTeX · CFF)

Цитата APA

warpdotdev. (2026). skill-doctor security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/warpdotdev-skill-doctor/audits/1

Цитата BibTeX

@techreport{warpdotdev-warpdotdev-skill-doctor-2026,
  author = {warpdotdev},
  title = {skill-doctor security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/warpdotdev-skill-doctor/audits/1},
  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: "skill-doctor security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "warpdotdev"
date-released: "2026-08-28"
url: "https://skillstore.io/skills/warpdotdev-skill-doctor/audits/1"
identifiers:
  - type: other
    value: "skillstore:warpdotdev-skill-doctor:audit:1"
    description: "Skillstore immutable audit report identifier"

Оценка Skillstore

Почему такая оценка Достоверность доказательств: Средний

Архитектура

Сопровождаемость

Контент

Сообщество

Соответствие спецификации

Что вы можете построить

Review Project Agent Performance

Score recent project conversations and identify repeated inefficiency or code-quality failures.

Audit Team Skill Adoption

Measure which installed skills appear in sampled sessions and where trigger descriptions may fail.

Prepare Skill Improvements

Generate evidence-linked draft edits and review diffs before changing live skill files.

Попробуйте эти промпты

Grade This Project

Grade recent conversations in this repository. Evaluate project and global skills, then show the report and proposed changes.

Review Selected Projects

Analyze conversations from these project paths: [paths]. Use the last [days] days and sample at most [count] sessions.

Audit Project Skills Only

Grade conversations for [project]. Evaluate project skills only, exclude subagents, and explain every recommendation with failed-session evidence.

Run a Cross-Harness Audit

Analyze all local conversations across supported harnesses. Include subagents, compare recurring failures, and draft only improvements supported by repeated evidence.