Back to skill

Security audit

Humanizer AI

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only writing rewrite skill with a broad activation phrase but no evidence of hidden execution, data access, persistence, or exfiltration.

Install only if you want an assistant to actively rewrite text to remove AI-sounding phrasing. For provenance-sensitive work such as school, legal, compliance, or disclosure-bound writing, ask explicitly for ordinary copyediting instead of de-AI humanization.

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
  • 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
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill's trigger phrases are broad enough to match routine editing and polishing requests, not just explicit requests to humanize AI text. This can cause the skill to activate in contexts where users did not intend de-AI rewriting, increasing the chance of unnecessary transformation of content, including concealment of AI authorship or bypass of policies that depend on preserving provenance or tone.

Content

No source excerpt is available for this finding.