ClawHub
Back to skill

Security audit

Agent Orchestration Patterns

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only guide for coordinating multiple AI agents, with its sensitive behaviors disclosed and aligned to that purpose.

Before installing, understand that the skill encourages multi-agent workflows that may share project context with sub-agents and use external model APIs. Keep tool permissions scoped, use environment variables for API keys, and require confirmation for writes, deletes, git operations, CI/CD changes, and other high-impact actions.

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

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 359)May include surrounding context.

Tool Permissions

Sub-agents may: read files, search code, run tests Sub-agents may NOT: push to git, modify CI/CD, delete files without confirmation

text

### ACP Server Setup

Static analysis

No suspicious patterns detected.