ClawHub
Back to skill

Security audit

ym-html-deck-builder

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to safely create a local HTML slide deck from a Markdown outline, with only minor scoping and locale caveats.

Install this if you want a zero-dependency local HTML slide generator. Be aware it writes or overwrites deck.html in the directory where it runs, expects UTF-8 Markdown input, and is primarily tailored for Chinese-language decks rather than PowerPoint/PDF export.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill describes creating and overwriting a local output file (`deck.html`) and instructs execution of a Python script, but it declares no explicit tool scope such as file-write permissions. In an agent environment, missing scope declarations can lead to broader-than-expected file access or unsafe execution assumptions, increasing the chance of unauthorized local file modification.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description says to use the skill when the user mentions phrases like「做个PPT」or「生成幻灯片」, which are broad everyday requests that could match many different presentation-related skills. The file does not provide exclusion conditions or tighter scope boundaries to distinguish when this HTML-only deck builder should activate instead of other slide-generation skills.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger list includes phrases like「做个PPT」and「生成幻灯片」without specifying output format, environment, or limitations. Because the skill is specifically for generating a local HTML slide deck, the current trigger list is too unspecific and may cause unintended invocation for ordinary PowerPoint or slide requests.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
Lines L82-L88 explicitly state '中文字体栈（必写全）' and provide a mandatory Chinese font stack for the skill output. This imposes a language/locale-specific requirement without user opt-in or a clearly documented region-specific justification, which matches the natural-language locale policy violation criteria.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The module docstring and all CLI/user-facing messages are written in Chinese, and the generated HTML explicitly sets lang="zh-CN". This imposes a specific language/locale on users without any opt-in, choice, or stated region-specific justification, which matches the natural-language locale policy violation criteria.

Static analysis

No suspicious patterns detected.