ClawHub
Back to skill

Security audit

What Buffett Would Do

Security checks across malware telemetry and agentic risk

Overview

This is a lightweight company-research triage skill with no executable code or hidden data access, though its broad activation phrases may trigger on generic investment questions.

Reasonable to install as a research aid. Treat outputs as a starting point rather than financial advice, and avoid sharing brokerage logins, wallet keys, API keys, private portfolio files, or other sensitive financial details.

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
91% confidence
Finding
The trigger phrases "Should I research [company/ticker]?" and similar natural-language patterns are broad enough to match ordinary conversation, which can cause the skill to activate when the user did not explicitly intend to invoke it. In a multi-skill environment, this can hijack routing, suppress more appropriate skills, or cause unintended investment-oriented output to be generated from casual prompts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.