Mackerel

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

Overview

This Mackerel skill is coherent, but it gives an agent broad authenticated access to run Mackerel actions and raw API requests, including write and delete methods, without clear confirmation boundaries.

Install only if you trust Membrane to broker access to your Mackerel account. Use a least-privileged Mackerel account where possible, prefer discovered Membrane actions over raw proxy calls, and require explicit user approval before any POST, PUT, PATCH, or DELETE request.

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 (1)

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The skill description is broad enough to match generic 'manage data, records, and automate workflows' requests, which can cause the agent to invoke this integration outside clearly scoped Mackerel-related tasks. Over-broad routing increases the chance of unintended external actions or data access when a user request is ambiguous.

VirusTotal

62/62 vendors flagged this skill as clean.