ClawHub
Back to skill

Security audit

Mermaid Architect

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides Mermaid diagram-writing guidance and does not request sensitive access or install executable behavior.

This appears safe to install for Mermaid diagram assistance. Be aware that vague prompts like "draw this" or "visualize" may activate it when you meant something other than a Mermaid diagram, so ask explicitly when you want another format.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The description includes ambiguous cues like 'Use this skill when the user asks for diagram, flowchart, sequence diagram, or visualize this process,' where 'visualize this process' is especially broad and could overlap with many non-diagram tasks. This ambiguity can lead to inappropriate skill invocation, increasing the attack surface for prompt-routing mistakes and unintended handling of arbitrary user input.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger phrases are broad enough to match many ordinary user requests such as 'Draw this' or 'Visualize', which can cause the skill to activate outside a clearly diagram-specific context. Over-broad invocation increases the chance of unintended routing, where user content is transformed into Mermaid output when another skill or safer default behavior would be more appropriate.

Static analysis

No suspicious patterns detected.