ClawHub
Back to skill

Security audit

Evidence-First Stock Research

Security checks across malware telemetry and agentic risk

Overview

This skill is a bounded stock-research assistant with clear no-trading and no-credential safeguards.

Install this if you want structured stock research, not trading automation. Treat outputs as general research only, verify dated sources independently, and do not provide broker credentials, account details, portfolio values, or instructions that would turn the research into an executable trade.

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
92% confidence
Finding
The skill combines a broad default prompt with allow_implicit_invocation: true, which can cause the agent to activate this research capability in contexts the user did not explicitly request. In a financial domain, unintended invocation can inject stock-analysis framing, produce quasi-investment guidance, or trigger use of stale or inappropriate research assumptions, increasing the risk of unsuitable or misleading output.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.