ClawHub
Back to skill

Security audit

Deslop the Copy

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed writing-editing skill with no code execution, data access, or hidden side effects, though its broad triggers and strict style rule may affect ordinary copy-editing requests.

Install this only if you want a persistent editing preference that removes AI-sounding patterns and avoids em dashes. Use explicit prompts when you want different punctuation, source fidelity, or a lighter copy edit.

SkillSpector

By NVIDIA
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
Confidence
89% confidence
Finding
The README advertises very broad invocation phrases such as 'Clean up this copy' and 'Make this not sound like AI' that overlap with ordinary writing-editing requests. In skill-based agent environments, overly generic triggers can cause the skill to activate unexpectedly and steer unrelated user tasks into its rewrite policy, creating prompt-squatting and unintended behavior risks.

Natural-Language Policy Violations

Low
Confidence
80% confidence
Finding
The README states that em dashes are 'never allowed in the output,' imposing a rigid style transformation regardless of user preference or source-text fidelity. While not directly security-critical, this is a policy-overreach issue because the skill can silently override user intent and alter content characteristics beyond the requested scope.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.