PostHog Query

• Outcome: Pass
• Latest audit: May 28, 2026 at 3:46 AM UTC
• Version:
  1.0.0

Overview

This skill is a straightforward PostHog query helper that uses the PostHog CLI and local PostHog credentials for read-only analytics queries.

Install this only if you trust the posthog-cli package source and intend your agent to query your PostHog analytics. Use a minimal query:read API key, protect ~/.posthog/credentials.json, and prefer scoped or aggregated queries when results could include user identifiers, URLs, or behavioral data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill explicitly instructs users to query product analytics data and notes that authentication is read from a locally stored credentials file, but it does not warn that the queried data may contain privacy-sensitive event properties, URLs, or user-behavior information. In an agent context, this increases the risk of overbroad querying or accidental exposure of analytics data because the capability is presented as routine and unrestricted.

VirusTotal

64/64 vendors flagged this skill as clean.