posthog-analytics

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides integration patterns for official and well-known PostHog libraries (posthog-js, posthog, posthog-node).
  • [SAFE]: The content includes explicit security guidance, advising against tracking sensitive data like passwords or credit card numbers, and provides a property sanitization function to remove potentially sensitive keys from event payloads.
  • [SAFE]: Environment variables are used for configuration, following industry standards for secret management. The regex pattern provided for credentials.md is a defensive measure to help detect and prevent accidental secret leakage.
  • [INDIRECT_PROMPT_INJECTION]: The skill outlines usage of MCP tools to programmatically create dashboards and insights, which introduces a data ingestion surface. 1. Ingestion points: User-provided dashboard names, descriptions, and query parameters in SKILL.md. 2. Boundary markers: Not present in the tool invocation snippets. 3. Capability inventory: Includes dashboard creation and query execution tools. 4. Sanitization: A dedicated 'Property Sanitization' section provides logic to filter sensitive keys before transmission, mitigating the impact of potential injections.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:05 AM
Security Audit — agent-trust-hub — posthog-analytics