ClawHub
Back to skill

Security audit

impactful-writing

Security checks across malware telemetry and agentic risk

Overview

This is a plain writing-assistance skill with broad activation language but no hidden commands, data access, persistence, or privileged behavior.

Install this if you want broadly applicable writing and editing guidance. Be aware it may activate for many writing-related prompts, so users who prefer narrower behavior may want to tighten the description or activation criteria.

SkillSpector

By NVIDIA
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
Confidence
95% confidence
Finding
The skill description is extremely broad ('use when writing or editing any text'), which can cause it to activate for a large fraction of ordinary user requests. Overly broad routing is risky because it increases unintended invocation, expands the skill’s influence beyond a narrow purpose, and can interfere with safer or more specific skills by capturing generic prompts.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.