ClawHub
Back to skill

Security audit

Humanizer

Security checks for vulnerabilities and agentic risk

Overview

This is a text-editing skill that rewrites AI-sounding prose and does not contain hidden code, persistence, network behavior, or credential handling.

Install only if you want an opinionated prose-rewrite helper. For sensitive, formal, quoted, legal, academic, medical, or compliance text, ask the agent to preserve meaning, citations, neutrality, and original voice before invoking it.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
96% confidence
Finding
The activation condition, "when editing or reviewing text to make it sound more natural and human-written," is broad enough to trigger on many ordinary writing tasks where the user may not want style transformation. Unintended invocation could cause the agent to rewrite content unnecessarily, alter tone or meaning, or interfere with domains where preserving original wording matters.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill directs the agent to impose a specific "human" style and even to "add soul" and inject personality without requiring user preference or consent. In practice, this can override the desired register, introduce first-person opinions or emotional framing, and distort factual, neutral, or institutionally appropriate text.

Static analysis

No suspicious patterns detected.