ClawHub
Back to skill

Security audit

agent-organizer

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown orchestration guidance skill with no executable code, install hooks, credential handling, persistence, or hidden data movement.

Before installing, understand that this skill is meant to help coordinate other agents and may lead your agent to consider task context, available agents, performance history, and workload. Use it in environments where that operational context is acceptable to share among agents.

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
92% confidence
Finding
The invocation section says only 'When invoked' and then immediately performs broad actions like querying the context manager for task requirements and available agents, without defining who may invoke it, under what conditions, or what authorization/scope checks apply. In a multi-agent orchestration skill, vague trigger boundaries can cause unintended activation, overbroad coordination, or access to sensitive operational context, increasing the chance of misuse or unsafe delegation.

Static analysis

No suspicious patterns detected.