ClawHub
Back to skill

Security audit

Financial Analysis

Security checks across malware telemetry and agentic risk

Overview

This is a plain financial-modeling prompt skill with no executable code, persistence, credential handling, or hidden data movement.

Installers should understand that this skill may activate on a wide range of valuation or returns questions. Use it for modeling and investor-material preparation from public or user-supplied inputs, and do not treat its output as personal financial, legal, tax, fiduciary, or trading advice without qualified review.

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
86% confidence
Finding
The description uses very broad invocation language such as 'any returns or valuation question,' which can cause the skill to activate for a wide range of ordinary financial prompts beyond a narrowly intended scope. Over-broad routing increases the chance that sensitive financial requests, regulated advice-like interactions, or mismatched tasks are handled by this skill without appropriate guardrails or user clarification.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.