ClawHub
Back to skill

Security audit

Brainstorming

Security checks for vulnerabilities and agentic risk

Overview

This brainstorming skill is mostly coherent, but it can activate very broadly and tells the agent to write and commit files without a clear final consent step.

Review this skill before installing if you do not want routine feature or behavior changes to invoke a brainstorming workflow. If installed, treat file creation and git commits as actions that should require your explicit approval before they happen.

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

High
Confidence
97% confidence
Finding
The skill description says it 'MUST' be used before any creative work, including very common development activities like creating features, adding functionality, or modifying behavior. That makes the invocation scope excessively broad and likely to trigger in many normal workflows, which can inappropriately route unrelated tasks through this skill and increase the chance of unnecessary repository inspection or follow-on actions. In context, this is more dangerous because the skill also instructs checking project files/commits and later writing documents and committing to git.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to write a design document to docs/plans and commit it to git, but it does not require explicit user confirmation immediately before those state-changing actions. This is risky because creating files and making commits modifies the user's workspace and version history; combined with the skill's broad invocation scope, these actions could occur during routine ideation without the user realizing the skill will persist changes.

Static analysis

No suspicious patterns detected.