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, with no evidence of hidden execution, exfiltration, persistence, or unrelated privileged behavior.

Install this if you want an agent to help revise prose to sound less AI-generated. Because it has Write/Edit permissions, use it on documents where file changes are expected, and ask the agent to show proposed edits first for important or sensitive text.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The manifest says to use the skill when 'editing or reviewing text,' which is a very common, expansive context rather than a specific trigger. It does not define narrower invocation phrases, boundaries, or exclusion cases, so the skill could be selected in many ordinary writing situations unintentionally.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The skill is granted Write and Edit capabilities, but the description and instructions do not clearly warn that it may directly modify files. In an editing workflow, that can cause unintended changes to user content if the agent invokes the skill proactively or applies rewrites without explicit confirmation, especially because the skill's process encourages producing revised drafts and final versions.

Static analysis

No suspicious patterns detected.