Fin Intel Hub

Security checks across malware telemetry and agentic risk

Overview

This is a coherent financial data lookup skill, but users should review it because its optional API keys may be exposed in raw error output despite stronger security claims.

Review before installing if you plan to provide API keys. Use it for public financial research, avoid entering private portfolio or proprietary trading details unless you accept third-party API requests, and avoid sharing logs or transcripts from failed calls because raw errors may reveal API keys.

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 description is excessively broad, ending with a catch-all phrase such as 'any financial data research and analysis tasks.' In agent ecosystems, broad triggers can cause the skill to be invoked for loosely related prompts, unnecessarily expanding its access to external data sources and increasing the chance of inappropriate tool use, prompt-routing mistakes, or data exfiltration through over-selection.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal