Ibanity

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real Ibanity banking integration, but it gives an agent broad authenticated access to financial API actions without clear confirmation safeguards.

Install only if you intend to let an agent work with Ibanity through Membrane. Use least-privilege or test access where possible, verify the Membrane CLI package/version, and require explicit confirmation before any payment, POST, PUT, PATCH, DELETE, or other account-changing request. Static scan was clean and VirusTotal was pending, so the concern is scope and financial authority rather than proven malware.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill documents both action execution and raw proxy requests against a financial API without requiring confirmation, safety gating, or warnings for state-changing operations. In a banking context, this increases the risk that an agent could modify remote records, trigger workflows, or initiate sensitive financial actions with insufficient user awareness.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal