ClawHub
Back to skill

Security audit

Amplitude Automation

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Amplitude automation guide that can read and change analytics data through Rube MCP, so it should be used carefully but does not show hidden or malicious behavior.

Install only if you intend to let an agent use a connected Amplitude account. Confirm the workspace, target users, event payloads, and cohort IDs before making changes, minimize exposure of raw user activity, and revoke the Rube/Amplitude connection when no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill explicitly enables user lookup and retrieval of detailed activity streams, but it provides no warning that these operations can expose sensitive behavioral analytics, identifiers, and potentially personal data. In an agent setting, this omission increases the chance that a model will perform privacy-impacting queries without confirming authorization, data minimization needs, or user consent.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill documents mutation operations for user properties and cohort membership, but it lacks safeguards warning that these actions can alter analytics state, segment membership, and downstream business decisions. Without confirmation and change-control guidance, an agent could make unauthorized or accidental modifications to production analytics data.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.