ClawHub
Back to skill

Security audit

Ai Humanizer

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only writing helper that rewrites user-provided text and does not request tools, credentials, persistence, or system access.

Install only if you want an agent to apply this style when you ask for rewriting or humanizing text. Review outputs carefully for factual drift, tone changes, and whether using 'undetectable' AI-style rewriting is appropriate for your context.

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
96% confidence
Finding
The README states that the skill activates automatically when it detects rewriting or humanizing intent, but it does not define clear boundaries for that detection. In an agent environment, overly broad auto-activation can cause the skill to intercept unrelated writing tasks and rewrite content unexpectedly, which may alter user output, override safer skills, or apply to sensitive text without explicit consent.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger language is very broad: it applies whenever a user asks to 'humanize, rewrite, or de-robot' text, which can overlap with many ordinary editing requests. In an agent ecosystem, such broad matching can cause this skill to activate unexpectedly, intercept prompts outside its intended scope, and transform content in ways that bypass user expectations or higher-priority safeguards.

Static analysis

No suspicious patterns detected.