ClawHub
Back to skill

Security audit

Team

Security checks for vulnerabilities and agentic risk

Overview

This is a short, conceptual team-orchestration skill with vague scope but no code, install behavior, persistence, credentials, network access, or hidden actions.

Before installing, understand that the skill is very general: it may be useful for framing team or multi-agent coordination, but you should not let it independently allocate money, credits, assets, permissions, or agents without explicit user approval and task-specific limits.

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
91% confidence
Finding
The skill description is highly generic and describes broad multi-agent orchestration, hierarchy, collaboration, and reward distribution without clear invocation boundaries or safety constraints. In an agentic environment, such vagueness can cause over-selection of the skill for unrelated tasks, expanding its authority and increasing the chance of unsafe delegation, coordination, or resource-routing behavior.

Static analysis

No suspicious patterns detected.