Flinks

• Outcome: Review
• Latest audit: May 29, 2026, 9:37 PM
• Version:
  1.0.4

Overview

This appears to be a legitimate Flinks/Membrane integration, but it gives agent-driven access to sensitive financial data without enough scope and confirmation guidance.

Install only if you are comfortable letting an agent use a Membrane-connected Flinks account. Prefer prebuilt read-only actions, require explicit confirmation before account, transaction, report, login, create, update, delete, or bulk requests, and revoke the Membrane connection when no longer needed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 81% confidence
• Finding: The skill description is broad enough that an agent could invoke it for loosely specified requests involving financial data without first confirming user intent, scope, or sensitivity. In a financial-data skill, over-broad triggering increases the chance of unnecessary access, connection setup, or downstream transmission of sensitive banking information.

Missing User Warnings

High

• Confidence: 94% confidence
• Finding: The documentation encourages running actions and proxy requests against a financial data platform but does not clearly warn that these operations may send highly sensitive financial information over the network. In this context, lack of an explicit disclosure/consent step can lead to accidental exfiltration of transaction, balance, login, or report data to third-party services.

VirusTotal

62/62 vendors flagged this skill as clean.