ClawHub
Back to skill

Security audit

ia-writing

Security checks across malware telemetry and agentic risk

Overview

This is an opinionated prose-editing skill with no executable code, network access, credential handling, or persistence.

Install this if you want an assertive prose editor that rewrites text toward a specific human, direct style. Review its edits before using them because it may change tone aggressively, but the artifacts do not show hidden execution, credential access, persistence, or data exfiltration.

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
91% confidence
Finding
The skill advertises broad triggers like "write, rewrite, edit, humanize, proofread, fix tone, or remove AI language" without clear boundaries, so it can be invoked for a wide range of ordinary requests even when a narrower or safer skill would be more appropriate. In an agent system, over-broad routing can cause unintended prompt takeover, letting this skill impose its own transformation rules on user content and reduce user control over output style or task selection.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.