ClawHub
Back to skill

Security audit

Multi-Agent Coordinator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed multi-agent coordination guide, with no bundled executable code or hidden install behavior.

Before installing, make sure you can read the documentation and are comfortable with the agent spawning task-specific sub-agents. Avoid sending secrets or sensitive private data to Learner, Critic, or shared ontology memory unless that is intended for the task.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The skill description begins in Chinese and does not indicate any option to adapt to the user's preferred language. This can cause user confusion, reduce transparency, and increase the chance that a user misunderstands the skill's behavior or operational limits, which is a legitimate quality and safety concern in agent-facing documentation.

Static analysis

No suspicious patterns detected.