Toolset

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.2

Overview

This Toolset skill is a real integration, but it gives an agent broad authenticated ability to change or delete connected WordPress/Toolset data without clear confirmation safeguards.

Install only if you trust Membrane and intend to let an agent operate on a connected Toolset/WordPress account. Prefer a least-privilege or staging account, review the Membrane connection permissions, and require the agent to ask before creating, updating, deleting, or using raw proxy API requests.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Vague Triggers

Medium

• Confidence: 85% confidence
• Finding: The skill description is broad enough to match generic requests about data, records, or workflow automation, which could cause the agent to invoke this skill outside the user's intended Toolset/WordPress context. Over-broad routing increases the chance of unnecessary external actions or data access, especially when the skill can connect to third-party systems and execute operations.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The documentation explicitly enables arbitrary proxy requests with methods including POST, PUT, PATCH, and DELETE, but does not require confirmation or warn about destructive side effects. In an agent setting, that creates a real risk of unintended state-changing or destructive operations against the connected service if the model misinterprets intent or follows unsafe prompts.

VirusTotal

64/64 vendors flagged this skill as clean.