Back to skill

Security audit

humanizer

Security checks for vulnerabilities and agentic risk

Overview

This is a plain writing-editing skill whose file-editing access matches its purpose, with no evidence of hidden execution, persistence, or data theft.

Install only if you want an agent to rewrite text for style. Review suggested edits carefully for legal, policy, security, academic, or compliance-sensitive writing, because the skill is designed to change tone and wording and may alter nuance.

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
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 (3)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
name: humanizer
version: 2.1.1
description: "Remove AI-sounding patterns from generated text"

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README tells the agent to act whenever asked to 'humanize' text or during document editing, which is a broad trigger not scoped to specific file types, trust boundaries, or user confirmation. Overly permissive activation can cause the skill to rewrite arbitrary content, including security-sensitive, legal, or policy text, and may be invoked in contexts where altering wording is unsafe or misleading.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This markdown file contains a section headed in Chinese with all troubleshooting and degradation guidance written only in Chinese. That imposes a specific language/locale on part of the skill documentation without user opt-in or justification, which fits the language-policy violation criteria.

Content

No source excerpt is available for this finding.