Swell

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Swell integration, but it gives an agent broad authenticated ability to read, change, or delete Swell business data through Membrane without clear guardrails.

Install only if you are comfortable letting Membrane-backed agents operate on your Swell account. Prefer discovered prebuilt actions, use a least-privilege Swell or Membrane account where possible, and require explicit approval before any raw proxy request or any POST, PUT, PATCH, or DELETE operation.

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: 90% confidence
Finding: The skill documents a generic proxy capability that can send arbitrary requests to the external Swell API, but it does not explicitly warn that using this path transmits user data off-platform. In an agent setting, that omission can lead to silent data disclosure or unintended write operations if the model chooses the proxy route without making the external transfer clear to the user.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal