Teamwork Desk

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Teamwork Desk integration, but it gives an agent broad authenticated help-desk access, including delete and raw API request capability, without clear safety guardrails.

Install only if you trust Membrane with the intended Teamwork Desk account and are comfortable giving an agent broad support-system access. Require explicit confirmation before any create, update, delete, settings, webhook, or proxy request, and ask the agent to show the exact target, method, payload, and expected effect before it runs.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Vague Triggers

Medium

Confidence: 80% confidence
Finding: The invocation text is broad enough that an orchestrator could select this skill for many generic Teamwork Desk requests, including operations unrelated to organization management. In a network-enabled integration that supports creation, updates, deletion, and proxy requests, over-broad triggering increases the chance of unintended data access or side-effecting actions being taken in the wrong context.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill advertises destructive actions like deleting tickets without any warning, confirmation requirement, or safety guidance. In an agent setting, omission of these guardrails can lead to accidental destructive operations, especially when the same skill also exposes broad CRUD functionality over customer support data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal