Back to skill

Security audit

docs-writer

Security checks for vulnerabilities and agentic risk

Overview

The skill fits its documentation purpose, with practical cautions about external tools and sharing private API details.

Use the skill within the intended project. Before following setup examples, review and pin external tools and choose whether global installation is appropriate; avoid the ambiguous mmdc package shorthand. Review generated API documentation before uploading it. Remove || true if rendering errors must fail CI. External npm package contents are outside this artifact review.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (35)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied command performs skill installation, not any of the declared technical-writing or Markdown-checking tasks. Although installing a documentation skill could be a setup step, installation is the only behavior shown, and the description does not disclose global installation or automatic confirmation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

安装目标的名称与声明的四类写作能力一致,但代码的全部实际行为是安装这些技能,而非提供或执行所声明的功能。全局安装及自动确认会改变运行环境,不只是文档生成过程中的内部实现细节。所示片段也未包含声明中的确定性 Markdown 检查脚本;无法据此验证安装后的技能是否具备这些功能。

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

Although this is an installation CLI rather than an MCP server, the command can download and execute an unpinned npm package. If a future resolved release is compromised, following this installation example could execute attacker-controlled code with the user's privileges; this is a conditional supply-chain risk, not evidence of current compromise.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The readme-generator installation example executes the unpinned skills npm CLI, exposing users to changes in the package resolved at installation time. The command is legitimate setup documentation rather than hidden agent behavior, but a compromised release could still execute code with the user's privileges.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The changelog-writer installation example uses an unpinned npm CLI, so the executable package can change without a documentation change. Although it is not an MCP server and no malicious release is demonstrated, a compromised resolved version could execute arbitrary code during installation.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The api-doc-generator installation example can fetch and execute an unspecified version of the skills npm package. This is ordinary installation guidance, but its mutable executable dependency creates a conditional supply-chain exposure with the user's execution privileges.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The diagram-architect setup command executes an unpinned external npm CLI rather than a fixed, reviewed release. The MCP classification is inaccurate, but a compromised future package version could still execute attacker-controlled code if the user follows the example.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

md
| 文档生命周期、生成顺序、自动vs手写、跨文档一致性 | [references/doc-lifecycle-and-pipeline.md](references/doc-lifecycle-and-pipeline.md) | 文档流水线 生成顺序 一致性 自动生成 受众 |
| API 文档撰写质量、REST/GraphQL 策略、版本演进 | [references/api-doc-authoring-playbook.md](references/api-doc-authoring-playbook.md) | OpenAPI REST GraphQL 版本 示例 鉴权 |
| 图表选型、PlantUML/Mermaid 决策、绘制与渲染坑 | [references/diagram-selection-guide.md](references/diagram-selection-guide.md) | 图表 PlantUML Mermaid 时序图 架构图 渲染 |
| README/项目文档生成(细粒度调用) | [skills/readme-generator/SKILL.md](skills/readme-generator/SKILL.md) | readme generator 项目文档 ARCHITECTURE |
| Changelog/Release Notes 生成(细粒度调用) | [skills/changelog-writer/SKILL.md](skills/changelog-writer/SKILL.md) | changelog release notes Keep a Changelog |
| API 文档生成(细粒度调用) | [skills/api-doc-generator/SKILL.md](skills/api-doc-generator/SKILL.md) | api doc OpenAPI swagger 端点 |
| 图表架构设计(细粒度调用) | [skills/diagram-architect/SKILL.md](skills/diagram-architect/SKILL.md) | diagram architect PlantUML Mermaid ER |

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

md
| 文档生命周期、生成顺序、自动vs手写、跨文档一致性 | [references/doc-lifecycle-and-pipeline.md](references/doc-lifecycle-and-pipeline.md) | 文档流水线 生成顺序 一致性 自动生成 受众 |
| API 文档撰写质量、REST/GraphQL 策略、版本演进 | [references/api-doc-authoring-playbook.md](references/api-doc-authoring-playbook.md) | OpenAPI REST GraphQL 版本 示例 鉴权 |
| 图表选型、PlantUML/Mermaid 决策、绘制与渲染坑 | [references/diagram-selection-guide.md](references/diagram-selection-guide.md) | 图表 PlantUML Mermaid 时序图 架构图 渲染 |
| README/项目文档生成(细粒度调用) | [skills/readme-generator/SKILL.md](skills/readme-generator/SKILL.md) | readme generator 项目文档 ARCHITECTURE |
| Changelog/Release Notes 生成(细粒度调用) | [skills/changelog-writer/SKILL.md](skills/changelog-writer/SKILL.md) | changelog release notes Keep a Changelog |
| API 文档生成(细粒度调用) | [skills/api-doc-generator/SKILL.md](skills/api-doc-generator/SKILL.md) | api doc OpenAPI swagger 端点 |
| 图表架构设计(细粒度调用) | [skills/diagram-architect/SKILL.md](skills/diagram-architect/SKILL.md) | diagram architect PlantUML Mermaid ER |

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/diagram-selection-guide.md (reported line 198)May include surrounding context.

md
- 直接服务子技能:
  - [skills/diagram-architect/](../skills/diagram-architect/SKILL.md)(主消费者)
  - [skills/readme-generator/](../skills/readme-generator/SKILL.md)(第 15 节:补全其架构图占位,按真实技术栈分层)
- 兄弟参考:
  - [references/doc-lifecycle-and-pipeline.md](doc-lifecycle-and-pipeline.md)(架构图在生成顺序中的位置与目录一致性)
  - [references/api-doc-authoring-playbook.md](api-doc-authoring-playbook.md)(API 文档中的时序图/架构图选区)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/doc-lifecycle-and-pipeline.md (reported line 181)May include surrounding context.

md
本文是 docs-writer 的**编排层**方法论:子技能各自负责「怎么生成单类文档」,本文负责「一个真实项目该按什么顺序产出哪些文档、什么自动/什么手写、跨文档如何保持一致」。

- 直接服务子技能:
  - [skills/readme-generator/](../skills/readme-generator/SKILL.md)(文档入口,生成顺序第 1 步;受众分层主文档)
  - [skills/changelog-writer/](../skills/changelog-writer/SKILL.md)(发布环节,生成顺序第 5 步;版本号一致性)
  - [skills/api-doc-generator/](../skills/api-doc-generator/SKILL.md)(生成顺序第 3 步;与实现一致性)
  - [skills/diagram-architect/](../skills/diagram-architect/SKILL.md)(生成顺序第 4 步;与代码目录一致性)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · skills/readme-generator/SKILL.md (reported line 7)May include surrounding context.

md
source:
  type: derived
  repo: skills-repo/docs-writer
  path: skills/readme-generator/SKILL.md
  version: 1.0.0
  updated: 2026-07-26
  url: https://skills.sh/jezweb/claude-skills/project-docs

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
| API 文档撰写质量、REST/GraphQL 策略、版本演进 | [references/api-doc-authoring-playbook.md](references/api-doc-authoring-playbook.md) | OpenAPI REST GraphQL 版本 示例 鉴权 |
| 图表选型、PlantUML/Mermaid 决策、绘制与渲染坑 | [references/diagram-selection-guide.md](references/diagram-selection-guide.md) | 图表 PlantUML Mermaid 时序图 架构图 渲染 |
| README/项目文档生成(细粒度调用) | [skills/readme-generator/SKILL.md](skills/readme-generator/SKILL.md) | readme generator 项目文档 ARCHITECTURE |
| Changelog/Release Notes 生成(细粒度调用) | [skills/changelog-writer/SKILL.md](skills/changelog-writer/SKILL.md) | changelog release notes Keep a Changelog |
| API 文档生成(细粒度调用) | [skills/api-doc-generator/SKILL.md](skills/api-doc-generator/SKILL.md) | api doc OpenAPI swagger 端点 |
| 图表架构设计(细粒度调用) | [skills/diagram-architect/SKILL.md](skills/diagram-architect/SKILL.md) | diagram architect PlantUML Mermaid ER |

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
| API 文档撰写质量、REST/GraphQL 策略、版本演进 | [references/api-doc-authoring-playbook.md](references/api-doc-authoring-playbook.md) | OpenAPI REST GraphQL 版本 示例 鉴权 |
| 图表选型、PlantUML/Mermaid 决策、绘制与渲染坑 | [references/diagram-selection-guide.md](references/diagram-selection-guide.md) | 图表 PlantUML Mermaid 时序图 架构图 渲染 |
| README/项目文档生成(细粒度调用) | [skills/readme-generator/SKILL.md](skills/readme-generator/SKILL.md) | readme generator 项目文档 ARCHITECTURE |
| Changelog/Release Notes 生成(细粒度调用) | [skills/changelog-writer/SKILL.md](skills/changelog-writer/SKILL.md) | changelog release notes Keep a Changelog |
| API 文档生成(细粒度调用) | [skills/api-doc-generator/SKILL.md](skills/api-doc-generator/SKILL.md) | api doc OpenAPI swagger 端点 |
| 图表架构设计(细粒度调用) | [skills/diagram-architect/SKILL.md](skills/diagram-architect/SKILL.md) | diagram architect PlantUML Mermaid ER |

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/doc-lifecycle-and-pipeline.md (reported line 182)May include surrounding context.

md
- 直接服务子技能:
  - [skills/readme-generator/](../skills/readme-generator/SKILL.md)(文档入口,生成顺序第 1 步;受众分层主文档)
  - [skills/changelog-writer/](../skills/changelog-writer/SKILL.md)(发布环节,生成顺序第 5 步;版本号一致性)
  - [skills/api-doc-generator/](../skills/api-doc-generator/SKILL.md)(生成顺序第 3 步;与实现一致性)
  - [skills/diagram-architect/](../skills/diagram-architect/SKILL.md)(生成顺序第 4 步;与代码目录一致性)
- 兄弟参考(同层增量方法论,按需交叉阅读):

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · skills/changelog-writer/SKILL.md (reported line 7)May include surrounding context.

md
source:
  type: derived
  repo: skills-repo/docs-writer
  path: skills/changelog-writer/SKILL.md
  version: 1.0.0
  updated: 2026-07-26
  url: https://skills.sh/patricio0312rev/skills/changelog-writer

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

md
| 图表选型、PlantUML/Mermaid 决策、绘制与渲染坑 | [references/diagram-selection-guide.md](references/diagram-selection-guide.md) | 图表 PlantUML Mermaid 时序图 架构图 渲染 |
| README/项目文档生成(细粒度调用) | [skills/readme-generator/SKILL.md](skills/readme-generator/SKILL.md) | readme generator 项目文档 ARCHITECTURE |
| Changelog/Release Notes 生成(细粒度调用) | [skills/changelog-writer/SKILL.md](skills/changelog-writer/SKILL.md) | changelog release notes Keep a Changelog |
| API 文档生成(细粒度调用) | [skills/api-doc-generator/SKILL.md](skills/api-doc-generator/SKILL.md) | api doc OpenAPI swagger 端点 |
| 图表架构设计(细粒度调用) | [skills/diagram-architect/SKILL.md](skills/diagram-architect/SKILL.md) | diagram architect PlantUML Mermaid ER |

## 内置脚本(确定性、可重复执行)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

md
| 图表选型、PlantUML/Mermaid 决策、绘制与渲染坑 | [references/diagram-selection-guide.md](references/diagram-selection-guide.md) | 图表 PlantUML Mermaid 时序图 架构图 渲染 |
| README/项目文档生成(细粒度调用) | [skills/readme-generator/SKILL.md](skills/readme-generator/SKILL.md) | readme generator 项目文档 ARCHITECTURE |
| Changelog/Release Notes 生成(细粒度调用) | [skills/changelog-writer/SKILL.md](skills/changelog-writer/SKILL.md) | changelog release notes Keep a Changelog |
| API 文档生成(细粒度调用) | [skills/api-doc-generator/SKILL.md](skills/api-doc-generator/SKILL.md) | api doc OpenAPI swagger 端点 |
| 图表架构设计(细粒度调用) | [skills/diagram-architect/SKILL.md](skills/diagram-architect/SKILL.md) | diagram architect PlantUML Mermaid ER |

## 内置脚本(确定性、可重复执行)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/api-doc-authoring-playbook.md (reported line 194)May include surrounding context.

md
## 相关子技能与层次边界

本文补 [skills/api-doc-generator/](../skills/api-doc-generator/SKILL.md) **装不下**的判断层:`api-doc-generator` 负责「从代码提取端点生成 OpenAPI」,本文负责「生成的 spec 怎么写才算好文档、REST vs GraphQL 策略、版本演进不破坏调用方、示例质量怎么保证」。

- 直接服务子技能:[skills/api-doc-generator/](../skills/api-doc-generator/SKILL.md)
- 兄弟参考:

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/api-doc-authoring-playbook.md (reported line 196)May include surrounding context.

md
本文补 [skills/api-doc-generator/](../skills/api-doc-generator/SKILL.md) **装不下**的判断层:`api-doc-generator` 负责「从代码提取端点生成 OpenAPI」,本文负责「生成的 spec 怎么写才算好文档、REST vs GraphQL 策略、版本演进不破坏调用方、示例质量怎么保证」。

- 直接服务子技能:[skills/api-doc-generator/](../skills/api-doc-generator/SKILL.md)
- 兄弟参考:
  - [references/doc-lifecycle-and-pipeline.md](doc-lifecycle-and-pipeline.md)(API 文档在生成顺序中的位置与一致性)
  - [references/diagram-selection-guide.md](diagram-selection-guide.md)(API 文档里的架构图/时序图选区)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/doc-lifecycle-and-pipeline.md (reported line 183)May include surrounding context.

md
- 直接服务子技能:
  - [skills/readme-generator/](../skills/readme-generator/SKILL.md)(文档入口,生成顺序第 1 步;受众分层主文档)
  - [skills/changelog-writer/](../skills/changelog-writer/SKILL.md)(发布环节,生成顺序第 5 步;版本号一致性)
  - [skills/api-doc-generator/](../skills/api-doc-generator/SKILL.md)(生成顺序第 3 步;与实现一致性)
  - [skills/diagram-architect/](../skills/diagram-architect/SKILL.md)(生成顺序第 4 步;与代码目录一致性)
- 兄弟参考(同层增量方法论,按需交叉阅读):
  - [references/api-doc-authoring-playbook.md](api-doc-authoring-playbook.md)(API 文档撰写质量)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · skills/api-doc-generator/SKILL.md (reported line 7)May include surrounding context.

md
source:
  type: derived
  repo: skills-repo/docs-writer
  path: skills/api-doc-generator/SKILL.md
  version: 1.0.0
  updated: 2026-07-26
  url: https://skills.sh/sickn33/antigravity-awesome-skills/api-documentation-generator

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 39)May include surrounding context.

md
| README/项目文档生成(细粒度调用) | [skills/readme-generator/SKILL.md](skills/readme-generator/SKILL.md) | readme generator 项目文档 ARCHITECTURE |
| Changelog/Release Notes 生成(细粒度调用) | [skills/changelog-writer/SKILL.md](skills/changelog-writer/SKILL.md) | changelog release notes Keep a Changelog |
| API 文档生成(细粒度调用) | [skills/api-doc-generator/SKILL.md](skills/api-doc-generator/SKILL.md) | api doc OpenAPI swagger 端点 |
| 图表架构设计(细粒度调用) | [skills/diagram-architect/SKILL.md](skills/diagram-architect/SKILL.md) | diagram architect PlantUML Mermaid ER |

## 内置脚本(确定性、可重复执行)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 39)May include surrounding context.

md
| README/项目文档生成(细粒度调用) | [skills/readme-generator/SKILL.md](skills/readme-generator/SKILL.md) | readme generator 项目文档 ARCHITECTURE |
| Changelog/Release Notes 生成(细粒度调用) | [skills/changelog-writer/SKILL.md](skills/changelog-writer/SKILL.md) | changelog release notes Keep a Changelog |
| API 文档生成(细粒度调用) | [skills/api-doc-generator/SKILL.md](skills/api-doc-generator/SKILL.md) | api doc OpenAPI swagger 端点 |
| 图表架构设计(细粒度调用) | [skills/diagram-architect/SKILL.md](skills/diagram-architect/SKILL.md) | diagram architect PlantUML Mermaid ER |

## 内置脚本(确定性、可重复执行)