Amplitude Automation

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Amplitude automation skill that can read and change analytics data through Rube MCP, with no evidence of hidden or malicious behavior.

Install this only if you intend to let an agent act through a connected Amplitude account. Verify the workspace, user IDs, cohort IDs, and payloads before sending events, updating user properties, or changing cohort membership, and avoid exposing raw user activity unless necessary. Revoke the Rube/Amplitude connection when it is no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill enables sensitive analytics operations including user lookup, retrieval of individual activity histories, user property mutation, event ingestion, and cohort membership changes, but it provides no privacy, authorization, or data-minimization guidance. In practice, this can normalize access to personal behavioral data and allow an agent to expose, modify, or bulk-process user information without explicit user confirmation or scope checks.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal