Hugo博客发布免费版

• Outcome: Review
• Latest audit: Sep 16, 2026 · 10:21 AM UTC
• Version: 1.0.2

Overview

This Hugo blog publishing skill is mostly coherent, but it gives broad automatic publishing and local inspection instructions that deserve user review before installation.

Review this skill before installing. It is intended to publish to a Hugo blog, so Git and command execution are expected, but you should only use it in a known Hugo repository, require confirmation before any commit or push, inspect the staged diff, avoid broad wildcard staging, and avoid letting it read MEMORY.md/USER.md unless you explicitly approve that access.

A.I.G

Vulnerability Patterns

• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (2)

other

Warning

• Location: SKILL.md:278

Finding

Unnecessary Access to Persistent Agent Memory

Content

View full analysis

Remediation

View remediation

T09 · Insecure Skill Coding Practices

Error

• Location: SKILL.md:118

Finding

Command Injection Through Unvalidated Shell Placeholders

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (10)

Missing User Warnings

High

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The skill documents automatic git push to a remote repository without requiring user review or confirmation. In context, this can directly publish content, alter production-facing state, or leak sensitive drafts/configuration to a remote origin if the wrong files are staged or the repository is misidentified.

Content

No source excerpt is available for this finding.

Hidden Instructions

High

• Category: Prompt Injection
• Confidence: 70% confidence

Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

md

|----|---|----|
| 内容分析 | 自动提取标题、标签、分类 | `帮我发布这篇博客` |
| Front Matter 生成 | 生成 Hugo 标准格式 | 自动创建 YAML 头部 |
| 截断标记 | 自动添加 `<!--more-->` | 列表页显示摘要 |
| Git 推送 | 自动提交并推送 | `git push` |
| 标签映射 | 英文 slug 映射中文显示 | 自动创建 `_index.md` |
**技术实现要点**：核心能力基于`input_params`参数与`output_format`配置实现,支持创建/查询/修改/删除等操作模式,通过`config_options`进行运行时配置.

Hidden Instructions

High

• Category: Prompt Injection
• Confidence: 70% confidence

Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

md

|----|---|----|
| 内容分析 | 自动提取标题、标签、分类 | `帮我发布这篇博客` |
| Front Matter 生成 | 生成 Hugo 标准格式 | 自动创建 YAML 头部 |
| 截断标记 | 自动添加 `<!--more-->` | 列表页显示摘要 |
| Git 推送 | 自动提交并推送 | `git push` |
| 标签映射 | 英文 slug 映射中文显示 | 自动创建 `_index.md` |
**技术实现要点**:核心能力基于`input_params`参数与`output_format`配置实现,支持创建/查询/修改/删除等操作模式,通过`config_options`进行运行时配置.

Vague Triggers

High

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

An overly broad trigger condition can cause the skill to activate for ordinary content-generation requests outside its intended scope. In a skill with exec and git-related behavior, incorrect activation increases the chance of unintended file changes or publication-oriented actions being taken in the wrong context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The example trigger 帮我发布这篇博客 is a natural-language request that could be used in many contexts and does not clearly constrain invocation to a Hugo repository or this skill’s workflow. Without additional scope limits or exclusion conditions, it risks unintended invocation collisions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 82% confidence

Finding

The document prescribes mapping English slugs to Chinese display values and repeatedly frames generated labels and titles in Chinese without offering a language choice. This can violate language/locale policy when users expect another language or bilingual behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The manifest and overview consistently describe a focused tool for publishing a personal blogger's single Markdown article to a Hugo blog with front matter generation and git push. However, L063-L083 claim the skill supports generic '创建/查询/修改/删除', '导入/重置', and '导出/保存/转换' operation modes via abstract parameters, which is materially broader than the described Hugo publishing workflow.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The manifest positions the skill as a Hugo blog publishing tool that analyzes provided article content, generates front matter, inserts a more marker, and pushes via git. L180 instead says the skill should be used when generating marketing copy, writing content, and optimizing titles, which broadens the advertised behavior into content creation tasks outside the declared publishing automation scope.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

Automatically reading MEMORY.md, USER.md, and .git configuration without an explicit privacy notice or task-scoped need can expose sensitive personal data, repository metadata, remotes, usernames, and tokens embedded in configuration. Because the skill has read and exec-related functionality, silent configuration harvesting increases privacy and secret-handling risk.

Content

No source excerpt is available for this finding.

Ssd 3

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

Instructions to automatically inspect memory files and git configuration may retrieve sensitive data from prior sessions or local repository settings without per-task necessity. This violates least-privilege and data-minimization principles, and could surface secrets or private operational details into the model context or outputs.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.