ClawHub
Back to skill

Security audit

Mighty Router

Security checks for vulnerabilities and agentic risk

Overview

Mighty Router is an instruction-only workflow skill that makes the agent more structured and strict during coding work, without hidden code execution or data collection.

Install this if you want stricter planning, verification, and high-risk edit handling. Expect the agent to be more rigid and concise, and to use special workflow formats for risky changes; avoid it if you need flexible response style more than enforced process.

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 applies itself to broad categories like code modification, research, or audit before requiring classification, which can let it steer many unrelated tasks and override normal user-directed behavior. In a security-sensitive agent, overly broad routing logic increases the chance that adversarial or simply mistaken instructions change execution mode, constrain analysis, or force unnecessary workflow steps.

Natural-Language Policy Violations

Low
Confidence
83% confidence
Finding
The skill hard-codes response-style constraints such as 'Keep responses brief, direct, and telegraphic' and 'No XML tags' without user opt-in, which can suppress useful detail or conflict with higher-priority system or task requirements. While not directly enabling code execution, this can degrade transparency and completeness during audits or verification, especially in safety-critical contexts.

Static analysis

No suspicious patterns detected.