ClawHub
Back to skill

Security audit

Autoreason Lite

Security checks across malware telemetry and agentic risk

Overview

This is a low-risk writing refinement skill that only defines a bounded review workflow and does not request sensitive access or install executable code.

Before installing, consider whether you want a refinement workflow to activate on broad requests like "improve this." Review outputs for factual accuracy and avoid sharing confidential drafts unless you are comfortable with the platform handling that content.

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
87% confidence
Finding
The trigger guidance is broad enough to match common phrases like 'improve this' or 'make this better,' which are ubiquitous in normal conversations. That can cause unintended invocation of the skill in contexts where iterative rewriting is unnecessary, increasing the chance of scope drift, hidden prompt expansion, extra token/cost usage, or interference with a more appropriate skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal