posthog-automation

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes an external MCP endpoint https://rube.app/mcp to provide its core functionality. This is a standard configuration for MCP-based skills to provide tool access.- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it retrieves and processes data from external PostHog environments.
  • Ingestion points: Event logs and feature flag configurations are retrieved via POSTHOG_LIST_AND_FILTER_PROJECT_EVENTS and POSTHOG_RETRIEVE_FEATURE_FLAG_DETAILS.
  • Boundary markers: Absent; the skill does not define specific delimiters to isolate external data from the agent's instructions.
  • Capability inventory: The agent has the ability to create events, manage projects, and configure feature flags.
  • Sanitization: Absent; there are no instructions to validate or sanitize the contents of retrieved event properties or metadata before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 07:28 PM