Teamwork

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.4

Overview

This appears to be a legitimate Teamwork integration, but it grants broad authority to read, change, and delete Teamwork data without clear confirmation guardrails.

Install only if you trust Membrane and want an agent to work with your Teamwork account. Use a least-privileged Teamwork account where possible, require explicit confirmation before create, update, complete, delete, or raw proxy requests, and revoke the Membrane connection when it is no longer needed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill description is broad enough to trigger on many ordinary requests involving Teamwork data, increasing the chance the agent invokes this capability without clear user intent or sufficient scoping. Because the skill can manage organizations and users and later exposes destructive operations, overbroad routing raises the risk of unintended access, modification, or deletion actions.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill advertises destructive actions like task deletion and completion without any warning, approval checkpoint, or confirmation guidance. In an agent setting, this can lead to irreversible or hard-to-recover state changes from ambiguous prompts, mistaken tool selection, or prompt injection affecting operational decisions.

VirusTotal

65/65 vendors flagged this skill as clean.