ClawHub
Back to skill

Security audit

Institutional 13F Tracker

Security checks across malware telemetry and agentic risk

Overview

This is a read-only financial data skill that uses a disclosed API key and network service, with some investment-signal wording users should treat cautiously.

Install only if you are comfortable giving SentiSense API access for financial-data lookups. Treat outputs as delayed 13F context, not real-time positions or investment advice, and avoid making trades solely from cross-source 'convergence' language.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The phrase describing cross-signal agreement as a 'high-conviction read' goes beyond neutral data presentation and nudges the model toward an investment thesis. In a financial-analysis skill, this can cause the agent to amplify signals into actionable-looking guidance despite repeated disclaimers that the tool is informational only.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
Saying matched signals are 'the read worth surfacing' is advisory language that prioritizes a specific market interpretation for the user. That framing increases the chance an agent will convert descriptive ownership data into implied buy/sell guidance, which is especially risky in a finance skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.