ClawHub
Back to skill

Security audit

dependency-graph

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent, read-only dependency-graph helper, with only minor caution around broad activation triggers and sending generated diagrams to a Mermaid rendering tool.

Before installing, be aware that this skill may activate for broad refactoring or coupling-analysis requests and may use a Mermaid rendering MCP with the generated graph. It appears suitable when you are comfortable allowing read-only repository structure analysis for dependency visualization.

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
95% confidence
Finding
The trigger list is broad and loosely bounded, so the skill may activate in routine code-analysis or refactoring conversations where the user did not explicitly request dependency-graph generation. This can cause unintended tool/agent dispatch and expand the skill’s operational surface, though the skill content itself is read-only and focused on visualization rather than performing dangerous actions.

Static analysis

No suspicious patterns detected.