ClawHub
Back to skill

Security audit

Flow State

Security checks for vulnerabilities and agentic risk

Overview

This is a simple productivity-coaching skill with broad flow-state advice and no code, tools, data access, installation behavior, or persistence.

Install only if you want lightweight flow-state coaching. Do not treat its speed-focused advice as permission to skip review, testing, legal/medical/financial caution, or security checks in high-risk tasks.

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
88% confidence
Finding
The note 'Works with any other skill — just layer it on top' gives the skill an effectively universal trigger scope, encouraging application in all contexts without boundaries or safety checks. In this specific skill, the guidance also discourages self-auditing ('Don't audit yourself mid-stream'), which can amplify risky behavior when combined with sensitive, regulated, or security-critical tasks.

Static analysis

No suspicious patterns detected.