ClawHub
Back to skill

Security audit

AI Content Humanizer Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed text-rewriting helper with expected file read and edit access, but users should be mindful of whole-document rewrites, paid calls, and authorship expectations.

Install only if you want an agent to rewrite AI-generated or AI-sounding text. Use it deliberately, review diffs before saving broad rewrites, and avoid using it to misrepresent authorship where that would violate academic, workplace, or platform rules.

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
92% confidence
Finding
The skill description is very broad and covers generic rewriting and humanization tasks across many contexts, which makes it likely to activate on common user prompts even when the user did not explicitly intend to invoke this specific skill. Over-broad activation increases the chance of unintended tool use, surprise billing, and application in sensitive contexts such as academic integrity evasion or deceptive content polishing.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The example trigger phrase 'Humanize all content in draft.md for professional use' is generic enough to match ordinary editing requests and could cause the skill to run on entire documents without strong user confirmation. This makes accidental invocation more likely and can amplify downstream risks such as costly bulk rewrites, inappropriate modification of sensitive files, or use to disguise AI-generated or policy-sensitive text at scale.

Static analysis

No suspicious patterns detected.