Viral Loops

Security checks across malware telemetry and agentic risk

Overview

This appears to be a normal Viral Loops integration, but it can act on live referral-program data through broad API access.

Install only if you trust the Viral Loops/Membrane connection path and intend to let the agent read or change Viral Loops campaign and referral data. For destructive or bulk changes, ask the agent to show the exact endpoint, method, affected records, and payload before it runs the command.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The skill description is quite broad ('Manage data, records, and automate workflows') and could cause the agent to invoke this integration for loosely related requests without clear user intent. In a skill that can access and potentially modify third-party SaaS data, overbroad routing increases the chance of unintended reads or writes to Viral Loops resources.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The documentation explicitly enables raw proxied API requests and lists mutating methods like POST, PUT, PATCH, and DELETE without any safety guardrails or confirmation requirements. That makes it easy for an agent to perform destructive or irreversible operations against live Viral Loops data, especially when prebuilt actions are insufficient or ambiguous.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal