ClawHub
Back to skill

Security audit

Multi Agent Orchestrator

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only guide for organizing AI agent teams, with disclosed coordination and scheduling examples but no hidden code or data theft behavior.

Install only if you want structured help designing multi-agent workflows. Before applying its examples, review any AGENTS.md/rules files, shared directories, cross-session messages, or cron jobs it proposes, because those can affect future agent behavior or run periodically if you choose to create them.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger list is very broad and includes generic phrases like 'multi-agent', 'agent team', and 'agent roles', which can activate the skill during ordinary discussion rather than when the user explicitly wants orchestration help. In an agentic environment, over-broad activation can inject irrelevant instructions and workflow changes into unrelated tasks, causing mis-execution or confusing delegation behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The daily standup and weekly summary templates are written in Chinese and presented as the required report format, with no indication that other languages are allowed. This imposes a specific language convention without user opt-in or documented regional justification, which is a natural-language policy violation under the locale/language rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The case study prominently uses Chinese names and labels in the organizational diagram, but the file does not state that the skill is region-specific or give users a language/locale choice. This can conflict with a language/locale policy requiring opt-in or documented justification for non-default language constraints.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.