ClawHub
Back to skill

Security audit

Research Workflow Orchestrator

Security checks for vulnerabilities and agentic risk

Overview

This is a small Markdown-only coordination skill for routing research work, with no code execution, persistence, credential use, or hidden data handling found.

Before installing, understand that this skill may cause an agent to coordinate or split research work across agents when a task crosses responsibilities. It is appropriate for lightweight planning and handoffs, but users should avoid applying it to sensitive workflows unless they explicitly want multi-agent coordination.

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
Confidence
90% confidence
Finding
The skill description is overly broad ('coordinate local research work across multiple agents and tools') and does not define clear trigger conditions, boundaries, or exclusions. In practice, this can cause the orchestrator to be invoked for tasks outside its intended scope, increasing the chance of unsafe delegation, unnecessary multi-agent decomposition, or routing of sensitive work without explicit guardrails.

Static analysis

No suspicious patterns detected.