ClawHub
Back to skill

Security audit

orchestrator

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only orchestration guide whose broad routing is disclosed and aligned with its purpose, with no executable install, persistence, credential, or exfiltration behavior found.

Before installing, understand that this skill may encourage routing broad project requests to specialist agents and parallel workflows. Use it when you want orchestration help, and review its proposed agent choices before sharing sensitive project context or approving large changes.

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
95% confidence
Finding

The routing table uses very broad, ambiguous trigger phrases such as 'design', 'review', 'test', 'security', and 'ui', which can match many unrelated requests and cause the orchestrator to invoke inappropriate specialists or unnecessary multi-agent flows. In an orchestration skill, misrouting is security-relevant because it can expand task scope, send sensitive context to the wrong downstream agent, and increase the chance of unsafe or unintended actions being taken.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.