Back to skill

Security audit

Humanizer Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward text-editing helper with no hidden code, networking, persistence, or unrelated privileges found.

Before installing, understand that this skill is meant to revise text and may edit files when invoked on documents. Use it on content you are comfortable having rewritten, and review changes before accepting them, especially where tone, factual precision, or attribution matters.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The phrase "Or invoke directly when editing documents" does not specify what exact trigger, context, or constraints activate the skill. Because this README is a markdown file, ambiguous activation guidance falls under vague triggers and could cause the skill to be invoked in overly broad situations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The invocation guidance says to use the skill when 'editing or reviewing text to make it sound more natural and human-written,' which is a wide, common writing scenario rather than a narrowly defined trigger. The file does not provide explicit trigger phrases, exclusions, or negative examples to clarify when this skill should or should not activate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The manifest declares Write and Edit as allowed tools, indicating the skill can modify user content, but the description and task sections do not clearly disclose that it may change files or ask before applying edits. For markdown files, missing warnings about actions that affect user data should be flagged when the behavior is not clearly disclosed.

Content

No source excerpt is available for this finding.