PostHog

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed PostHog integration that needs a Maton API key and can access sensitive analytics data, but its behavior matches its stated purpose.

Install only if you trust Maton to proxy your PostHog account data. Keep MATON_API_KEY private, choose the intended connection when multiple accounts are linked, minimize retrieval of persons and session recordings, avoid exposing raw emails or replay details unless necessary, and approve write operations only after checking the exact project, resource, and effect.

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 (1)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill exposes access to highly sensitive analytics artifacts such as persons data, user properties, and session recordings, but it does not prominently warn operators that these endpoints may reveal PII, behavioral telemetry, or replay data. In a skill intended for agent use, lack of an explicit data-sensitivity warning increases the risk of over-collection, unsafe disclosure to users, and querying sensitive data without informed consent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal