ClawHub
Back to skill

Security audit

Brainstorming

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward brainstorming workflow that may create a visible design document but does not request sensitive access or perform hidden actions.

Install this if you want the agent to slow down and clarify vague or complex feature work before coding. Expect it to ask questions, present alternatives, and possibly create a visible design document in docs/design; review that document before letting the agent proceed to implementation.

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
89% confidence
Finding
The activation guidance says to trigger the skill when a user request is vague and gives examples like "make it better" and "add feature X." These phrases are broad and could overlap with common requests, while the file does not provide negative examples or clearer constraints for when the skill should not activate.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The markdown directs the agent to save a design document to `docs/design/YYYY-MM-DD-feature-name.md`, which affects the user's filesystem. The description does not warn that the skill may create or modify files, so users may not realize it performs a write operation.

Static analysis

No suspicious patterns detected.