ClawHub
Back to skill

Security audit

architecture-diagram

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward architecture-diagram helper that reads code structure and produces Mermaid diagrams without hidden install, persistence, or destructive behavior.

Before installing, be aware that diagram generation may examine the project root if you do not provide a narrower scope, and rendered diagrams may be passed to the configured Mermaid Chart MCP service. Use an explicit scope for sensitive repositories.

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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The manifest trigger "visualizing how plugins or modules fit together" is a natural-language activation condition that is fairly broad and lacks explicit constraints or exclusion examples. It could match ordinary architecture or explanation requests beyond a narrowly defined invocation scope, increasing the chance of unintended activation.

Static analysis

No suspicious patterns detected.