ClawHub
Back to skill

Security audit

Mermaid Diagram

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk Mermaid diagram helper with no code execution, network access, credential handling, or persistence.

Installers should understand this skill will guide the agent to return Mermaid diagram code and may activate on broad diagram-related Chinese keywords. It does not appear to run commands or access private data.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
| 项目时间线 | Timeline | `timeline` |
| 用户旅程 | Journey | `journey` |

## Output Rules

1. Always wrap output in ` ```mermaid ` code blocks
2. Use Chinese labels when the user writes in Chinese
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The description says to use the skill for 'any request that mentions' several terms, including broad terms like '画图' and '流程图'. Those phrases can appear in ordinary conversation without clearly indicating the user wants this specific skill, and the file does not provide exclusion conditions or negative examples to narrow activation.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The title and description are entirely in Chinese, which indicates a fixed language choice in the skill content. Under the policy, forcing a specific language without user opt-in or documented justification can be a natural-language policy violation.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The instruction 'Use Chinese labels when the user writes in Chinese' enforces a language choice based solely on detected input language rather than offering a choice. This can violate language/locale policy when user-facing language should be selected by preference or explicit opt-in.

Static analysis

No suspicious patterns detected.