ClawHub
Back to skill

Security audit

Plg Playbook

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only business playbook with no evidence of code execution, data access, or hidden behavior.

Install this if you want product-led growth and freemium conversion guidance. Be aware it may activate during general SaaS conversations about activation, freemium, or self-serve, but the reviewed artifacts do not show hidden code, data collection, or privileged actions.

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
90% confidence
Finding
The trigger list includes very broad phrases such as "activation," "self-serve," and "freemium," which are common in general startup, product, and SaaS discussions. This can cause the skill to activate outside its intended scope, leading to prompt hijacking of unrelated conversations, user confusion, or unintended influence over agent behavior even though the content itself is business-focused rather than directly harmful.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.