ClawHub
Back to skill

Security audit

incident-routing-desk

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small incident-routing helper that produces assignment guidance and results without code execution, credentials, private-file access, persistence, or hidden behavior.

Install this if you want an assistant to help draft incident routing guidance and owner assignment results. Review generated assignments before treating them as operational decisions, especially when service profile, severity, or current incident context is incomplete.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill's top-level invocation guidance is broad enough that an orchestrator could select it for generic 'service assignment' requests without strong user intent for incident routing. That can cause unintended tool activation or business-action recommendations in the wrong context, especially because the skill exposes independently invocable stages and encourages stage execution based on loosely matched requests.

Vague Triggers

Medium
Confidence
94% confidence
Finding
Stage 2 says to use the skill when the user 'asks to assign an incident owner,' which is a vague trigger likely to match ordinary operational phrasing too broadly. In practice this can route unrelated requests into owner assignment logic and produce unauthorized or incorrect assignment decisions from incomplete or mis-scoped guidance.

Static analysis

No suspicious patterns detected.