ClawHub
Back to skill

Security audit

Prompt To Skill Router

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown routing guide that helps decide whether to answer directly or use skills, without adding executable code, persistence, or data access.

Before installing, understand that this skill may influence how often the agent discusses skill routing. It appears safe as a decision aid, but users who prefer minimal routing commentary may want narrower activation wording.

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
92% confidence
Finding

The activation criteria are broad enough to match many ordinary assistance requests, including situations where no specialized capability is needed. In an agent environment, this can cause over-triggering of the router skill, increasing prompt interception and unnecessary delegation decisions, which may degrade reliability, create routing loops, or crowd out more appropriate skills/direct handling.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.