Workato

Security checks across malware telemetry and agentic risk

Overview

This Workato skill is coherent, but it gives an agent broad enterprise automation powers without clear safety guardrails.

Install only if you trust Membrane and intend to let an agent operate on your Workato environment. Use least-privilege Workato/Membrane access, review the global npm CLI before installing, and require explicit human approval before any create, update, delete, deploy, run, trigger, or raw proxy request.

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: 86% confidence
Finding: The skill description is very broad ('Manage data, records, and automate workflows'), which can cause the agent to invoke this skill for many loosely related requests. In a skill that supports extensive read/write/delete operations and direct API proxying, overly broad activation increases the chance of unintended high-impact actions being selected without sufficient user confirmation.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The markdown advertises broad capabilities including create, delete, deploy, run, trigger, and a generic proxy request feature, but it does not include user-facing warnings or approval requirements for destructive or externally impactful actions. In a connected enterprise automation platform, this can lead to accidental modification of workflows, data, credentials, or operational state through ambiguous prompts or over-eager agent behavior.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal