技能 clinical-reports

📦

clinical-reports

Name: clinical-reports
Author: K-Dense-AI

内容修订 r1 高风险 ⚙️ 外部命令📁 文件系统访问

创建合规的临床报告

临床团队需要一致的报告，以保护患者隐私并满足发表或监管标准。此技能为病例报告、试验报告、诊断报告和患者记录提供模板、清单和本地验证器。

支持: Claude Codex Code(CC)

⚠️ 38 差

安装前请停下并请求确认。

请审查安装计划，并在更改文件前获得用户明确同意。

使用我的智能体安装

将此请求复制给你的智能体，其中包含权威 Skill 页面和清单。

智能体请求

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

你的智能体仍应展示其计划，并按安全策略请求必要确认。

Agent 可读资源

当 AI Agent、爬虫或脚本需要干净上下文，而不是读取完整页面时，请使用这些链接。

Markdown 详情 GET /skills/k-dense-ai-clinical-reports.md 已签名 manifest GET /api/skills/k-dense-ai-clinical-reports/manifest 已签名 lockfile GET /api/skills/k-dense-ai-clinical-reports/lockfile

测试它

正在使用“clinical-reports”。临床医生需要一份罕见药物反应病例报告大纲。

预期结果:

包含病例报告表述的简明标题。
结构化摘要，涵盖表现、诊断、干预和结局。
包含关键临床事件的已去标识化患者时间线。
将该病例与已发表文献进行比较的讨论部分。
提交前的知情同意和隐私清单。

正在使用“clinical-reports”。研究协调员需要根据试验记录生成 SAE 叙述。

预期结果:

受试者层面的事件叙述，包含发生时间、严重性标准、治疗和结局。
因果关系和预期性评估部分。
面向申办方、IRB 和监管报告的随访清单。
适合制表的不良事件类别摘要。

正在使用“clinical-reports”。质量负责人希望在发布前审核出院小结。

预期结果:

覆盖诊断、操作、用药、随访和患者指导的完整性审核。
针对标识符和敏感日期的隐私检查。
针对禁用缩写和不清晰用药措辞的术语审核。
供临床医生批准的简短更正清单。

安全审计

高风险

v7 • 2026/7/5 打开版本化报告

Most static findings are false positives caused by clinical terminology, Markdown backticks, and expected local report-output scripts. No evidence found of command injection, credential access, network calls, or hidden data exfiltration in the reviewed code. Two semantic risks remain: an included self-audit that claims safety and a mandatory external AI figure workflow that could expose clinical data.

已扫描文件

11,881

分析行数

复核项

已忽略误报

已确认安全问题 (2)

高

evaluation_output.json:18

Prompt Injection Attempt Detected

evaluation_output.json claims "no security concerns" and says "all static findings are false positives." This untrusted self-audit can bias automated reviewers and should not ship with the skill.

The file contains a direct safety claim about the package rather than operational code. It may be leftover evaluation output, but it is still untrusted content that can influence review.

高

SKILL.md:34-48

External AI Figure Workflow May Expose Clinical Data

SKILL.md mandates an AI-generated figure for every clinical report and directs users to a scientific-schematics workflow. Clinical report figure prompts may include patient timelines or trial data, creating a privacy exposure risk if not de-identified.

The text explicitly makes external AI figure generation mandatory and gives a workflow for clinical report diagrams. The privacy risk is inferred from the clinical-report domain and the referenced patient timelines.

风险因素

⚙️ 外部命令 (43)

📁 文件系统访问 (5)

scripts/check_deidentification.py:330 scripts/extract_clinical_data.py:86 scripts/format_adverse_events.py:86 scripts/generate_report_template.py:74 scripts/validate_case_report.py:318

审计者: codex 查看审计历史 →

分享与引用此报告

分享版本化评估报告、中性徽章、嵌入卡片和引用。Skillstore 只报告证据，不判断该 Skill 是否安全。

打开版本化报告

复制报告链接

https://skillstore.io/skills/k-dense-ai-clinical-reports/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/k-dense-ai-clinical-reports/security.svg)](https://skillstore.io/skills/k-dense-ai-clinical-reports?utm_source=security_passport_badge)

HTML 徽章

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

嵌入卡片

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

学术引用 (APA · BibTeX · CFF)

APA 引用

K-Dense-AI. (2026). clinical-reports security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-clinical-reports/audits/7

BibTeX 引用

@techreport{k-dense-ai-k-dense-ai-clinical-reports-2026,
  author = {K-Dense-AI},
  title = {clinical-reports security audit report (audit version 7)},
  institution = {Skillstore},
  year = {2026},
  number = {7},
  url = {https://skillstore.io/skills/k-dense-ai-clinical-reports/audits/7},
  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: "clinical-reports security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
  - name: "K-Dense-AI"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/k-dense-ai-clinical-reports/audits/7"
identifiers:
  - type: other
    value: "skillstore:k-dense-ai-clinical-reports:audit:7"
    description: "Skillstore immutable audit report identifier"

比较变体

2 个可安装变体

每位作者的技能都保持为独立的可安装项。推荐变体按 Skillstore 证据排序。

为什么此变体排名第一

Skillstore 评分最高

作者 / 来源 Skillstore 评分证据置信度 Skillstore 使用量已更新

davila7 推荐

davila7-clinical-reports

Skillstore 评分 86

证据置信度高

Skillstore 使用量 21

已更新

2026-09-09

K-Dense-AI 当前

k-dense-ai-clinical-reports

Skillstore 评分 38

证据置信度中

Skillstore 使用量 25

已更新

2026-09-09

Skillstore 评分

评分依据证据置信度: 中

架构

可维护性

内容

社区

规范符合性

你能构建什么

准备病例报告

使用已去标识化的患者详细信息、时间线、知情同意措辞和符合期刊投稿要求的章节，起草符合 CARE 要求的病例报告。

记录试验安全性

使用试验报告标准准备 SAE 叙述、不良事件摘要和临床研究报告大纲。

审核报告质量

检查患者记录和诊断报告的完整性、隐私风险、术语问题和合规缺口。

试试这些提示

起草病例报告

Draft a CARE case report for [condition] using de-identified details. Include title, abstract, timeline, interventions, outcomes, and consent note.

创建 SOAP 记录

Create a SOAP note for this de-identified encounter: [details]. Organize subjective history, objective findings, assessment, and plan.

构建试验安全性摘要

Prepare an SAE narrative and safety table summary from this de-identified trial data: [details]. Include causality, expectedness, outcome, and follow-up.

审计临床文档

Review this de-identified clinical report for HIPAA identifiers, unsafe abbreviations, missing regulatory elements, and inconsistent terminology. Return prioritized fixes.