ClawHub
Back to skill

Security audit

Brainstorming

Security checks for vulnerabilities and agentic risk

Overview

This is a brainstorming workflow skill with broad activation language, but it shows no hidden code, exfiltration, destructive behavior, or unsafe persistence.

Install this if you want a structured design-first workflow. Be aware that it may trigger for a wide range of creative coding tasks, inspect repository context, and ask the agent to write and commit a design document, so keep those actions user-approved in practice.

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
95% confidence
Finding
The skill declares it 'MUST' be used before any creative work, with broad examples like creating features, building components, adding functionality, or modifying behavior. This can cause the skill to trigger in many unrelated situations, steering the agent into unnecessary project inspection, design generation, document writing, and git actions even when the user did not ask for that workflow. In an agent system, such over-broad mandatory routing can create unwanted execution paths, increase data exposure to the skill, and interfere with safer or more appropriate task handling.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The manifest description creates a very broad activation rule by saying the skill MUST be used before any creative work, including creating features, building components, adding functionality, or modifying behavior. This can cause the skill to be invoked in many unrelated contexts, increasing the chance of workflow hijacking, prompt-scope expansion, and over-collection of user or project context beyond what is necessary.

Static analysis

No suspicious patterns detected.