ClawHub
Back to skill

Security audit

Writing Style Humanizer English

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward writing-rewrite skill, with the main caution that it may change tone or perspective if used too broadly.

Install only if you want an aggressive style editor for making text sound less AI-written. Review the final output for factual accuracy, preserved meaning, and unchanged authorship perspective, especially for legal, academic, professional, or sensitive writing.

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
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill description is broad enough to activate during generic editing or review workflows, which can cause the agent to rewrite text in situations where the user did not explicitly ask for style transformation. In practice this increases the chance of unintended content modification, including changing tone, authorship signals, or meaning-sensitive wording in professional, legal, academic, or safety-critical text.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The instruction to use first-person 'when it fits' and to add personality can push the model to introduce opinions or personal voice that were not present in the source. That creates a risk of misrepresenting the user's intent, fabricating perspective, or making edited text appear authored from lived experience when it was not.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.