ClawHub
Back to skill

Security audit

smart-sourcing

Security checks across malware telemetry and agentic risk

Overview

This skill only provides citation and verification guidance, with no code execution, persistence, credential access, or hidden data handling.

Before installing, understand that this skill may influence when an agent chooses to search and cite sources. It is suitable as lightweight sourcing guidance, but users doing legal, compliance, security, medical, or formal research should still require full verification standards.

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 terms are broad enough to match many ordinary requests about citations, accuracy, or efficiency, which can cause this skill to activate outside its intended niche. That can lead to inappropriate routing or over-application of its guidance, especially where security- or compliance-sensitive tasks require stricter sourcing behavior than this lightweight heuristic encourages.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.