ClawHub

Mixpanel

Security checks across malware telemetry and agentic risk

Overview

This Mixpanel skill appears purpose-aligned and uses expected Mixpanel credentials and API calls, with caution around broad activation and persistent memory of analytics context.

Install only if you intend the agent to access your Mixpanel project. Use a least-privilege Mixpanel service account, keep credentials in environment variables, and review or clear any saved memory containing product, customer, or analytics details.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The activation rule is broad enough to trigger on generic mentions of metrics or user behavior, which can cause the skill to engage in contexts the user did not clearly intend. That increases the chance of unnecessary data access, inappropriate tool use, or privacy-invasive behavior, especially when combined with stored preferences and analytics credentials.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill directs the agent to save user and project context into persistent memory without any disclosure or consent flow. Persistent storage of analytics goals, product details, and discovered insights can create privacy and data-governance risks if users are unaware that this information is retained across sessions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal