ClawHub
Back to skill

Security audit

Humanizer Enhanced

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed writing-assistant skill for scanning and rewriting drafts, with no code execution, persistence, credential access, or hidden data handling found.

Install this as a text rewriting helper, not as an automatic editor. Review proposed changes before accepting them, especially in batch mode, because it may substantially change voice, wording, formatting, and factual attribution in drafts.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises activation on broad natural-language phrases like "humanize this," "make it sound human," and general requests to clean up drafts or articles. This can cause over-triggering on ordinary editing requests, increasing the chance the agent applies a rewriting workflow when the user did not explicitly intend to invoke this skill, which may alter content unexpectedly or bypass more specific review-oriented skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.