Contis

Security checks across malware telemetry and agentic risk

Overview

This payment integration is not malicious, but it needs review because it can make broad authenticated API calls that may read or change sensitive financial data.

Review before installing. Use a least-privileged Membrane and Contis account, prefer sandbox testing first, and require explicit approval before any payment, card issuance, account change, POST/PUT/PATCH/DELETE request, or raw proxy call.

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: 89% confidence
Finding: The skill explicitly documents arbitrary proxy requests to the Contis API, including support for POST, PUT, PATCH, and DELETE, without requiring user confirmation or warning that sensitive financial/account data may be transmitted or modified. In a payments context, this increases the risk of unintended disclosure, state-changing operations, or destructive requests being performed through an agent with network access.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal