Back to skill

Security audit

Hekouwang Typora Theme

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Typora theme-engineering helper with local build/install steps and optional GitHub publishing, and I found no hidden persistence, exfiltration, or deceptive behavior.

Install this if you want help maintaining or publishing the hekouwang Typora theme. Before running commands from the cloned GitHub repository, review the scripts you will execute, confirm the Typora theme directory target, and double-check any `gh api` or `gh pr create` command because it can publish files to your fork and open a public PR.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The listed trigger phrases include broad terms such as "换肤", "做一套主题", and "Markdown 编辑器主题", which can match ordinary user requests outside the intended Typora-specific workflow. The description does not provide exclusion conditions or negative examples to clarify when the skill should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document is entirely written in Chinese and includes prescriptive statements such as '西文族必须全部排在中文族之前' and operational guidance without any indication that language choice is optional. Under the stated policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation unless the regional constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file contains natural-language statements such as '中文长文浅色 + 深色' and 'CJK 长文专用', which impose a language/locale scope in the skill description. The policy allows locale constraints when clearly documented and justified, but the changelog does not provide a compliance or region-specific justification, nor does it mention user opt-in or alternatives.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill file presents all instructions in Chinese and does not indicate that the language is optional, user-selectable, or required for a region-specific purpose. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown workflow instructs the user to create refs, upload files, and open a PR against a fork via gh api and gh pr create, which affects a remote repository. While the section title implies publishing, there is no explicit warning in the steps about remote write side effects or the fact that these commands will create branches and push content to GitHub.

Content

No source excerpt is available for this finding.