Back to skill

Security audit

caulsal-diagram

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward causal-diagram helper with no evidence of hidden access, credential use, network calls, or persistence.

Install this if you are comfortable with Chinese-language documentation and a local script that writes diagram PNGs to paths you choose. You may need to install Pillow separately for the image generator to run.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

代码的核心功能与‘绘制因果图/DAG’总体一致,且实现了图片生成这一部分,因此不存在完全不同的主用途,也没有发现越权访问、网络通信或其他无关能力。但声明中明确写到“支持生成图片和 Mermaid 代码两种输出格式”,而所给代码只实现了基于 Pillow 的图片绘制与保存,没有任何 Mermaid 文本/代码生成功能、相关参数、分支逻辑或输出路径。因此描述对能力范围有实质性夸大,属于 description 与 behavior 不完全匹配。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description is written as a Chinese-only instruction surface and does not indicate that users may request another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The module docstring, usage description, and CLI help text are presented in Chinese only, which can impose a language choice on users without opt-in. The policy explicitly calls for flagging language or locale constraints when they are forced and not justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The entire reference is written in Chinese, including the title, headings, examples, and usage notes, with no indication that users may choose another language. Under the policy rules, language-specific content can be a natural-language policy concern when it imposes a locale without explicit opt-in or documented justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.