ClawHub
Back to skill

Security audit

cro

Security checks across malware telemetry and agentic risk

Overview

This CRO guidance skill is coherent and low-risk, with only a minor chance of being invoked for ambiguous page-feedback requests.

Install if you want CRO recommendations for marketing pages and forms. Be aware it may activate on broad page-feedback wording, and it may read local product-marketing context files in the project to tailor its advice.

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
94% confidence
Finding
The eval expects the skill to trigger on very casual phrasing like 'this page isn't converting,' which is broad enough to match everyday complaints outside a clear CRO intent. In a skill-routing or invocation system, this can cause over-triggering, misrouting user requests, and accidental application of the CRO workflow where a more specific skill or general assistant behavior would be appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.