ClawHub
Back to skill

Security audit

multi-agent-coordinator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only coordinator for planning and combining work from other agents, with no hidden code, persistence, credential handling, or exfiltration behavior found.

Install this if you want help planning and coordinating complex work across multiple agents. Review its coordination plan before allowing many agents to run, since broad activation may be unnecessary for simple tasks and can share task context across selected 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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description is broad and trigger-oriented enough to match many generic planning, execution, and coordination requests, which can cause the system to invoke this skill outside narrowly intended scenarios. Because the skill is designed to orchestrate other agents and route work dynamically, overbroad activation increases the chance of unnecessary delegation, context leakage across agents, and unintended execution paths.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.