ClawHub
Back to skill

Security audit

Humanizer

Security checks for vulnerabilities and agentic risk

Overview

The skill has no executable or system-access behavior, but it is explicitly designed to disguise AI-generated writing and is broad enough to be used in deceptive contexts.

Install only if you want a transparent editing aid and will avoid using it to misrepresent authorship, bypass AI detectors, submit undisclosed AI-generated academic or professional work, or evade platform policies.

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
94% confidence
Finding
The skill description says to use it when editing or reviewing text to make it sound more natural and human-written, which is broad enough to trigger on many ordinary writing tasks. Because the skill is explicitly designed to remove signs of AI generation and includes anti-detection guidance, over-broad invocation increases the chance it will be applied in contexts involving policy evasion, academic dishonesty, fraud, or concealment of machine-generated content.

Static analysis

No suspicious patterns detected.