ClawHub
Back to skill

Security audit

brainstorming

Security checks for vulnerabilities and agentic risk

Overview

This is a plain brainstorming workflow skill with broad activation wording but no hidden code, network behavior, credential access, or unrelated actions.

Before installing, understand that this skill may activate often during feature or behavior changes, inspect project context, and create committed design documents. It appears safe, but teams that prefer explicit opt-in planning should narrow the trigger and require confirmation before committing files.

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

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill declares a mandatory trigger for essentially all creative or development-related work ('MUST use this before any creative work'), which gives it broad control over a large share of agent activity. Even though the body appears benign, this kind of forced interception can unnecessarily expand the skill’s influence, expose project context broadly, and create a choke point where future prompt changes or adversarial edits could steer behavior, collect sensitive context, or block normal workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.