ClawHub
Back to skill

Security audit

self-reflection

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed fact-checking workflow with no executable install behavior, persistence, or hidden data handling, though it may consume extra tools and subagent work when used broadly.

Install this if you want a rigorous fact-checking workflow. Be aware that broad use may launch multiple verification subagents and external source checks, so it can add time, cost, and tool activity for routine answers.

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
93% confidence
Finding
The activation description, "Use when you need to determine the accuracy of the answer," is very broad and can cause the skill to trigger in many routine situations. Overly broad routing increases the chance the agent invokes a workflow that spawns multiple verification subagents and loops unnecessarily, which can amplify cost, latency, and unintended tool usage from otherwise simple prompts.

Static analysis

No suspicious patterns detected.