posthog-automation

Warn

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct users to connect to a third-party MCP server at 'https://rube.app/mcp'. This server provides the tool definitions and execution environment for the PostHog automation. As this endpoint is not hosted by the official PostHog service or a widely recognized technology provider, the security of the operations depends entirely on the reliability of the third-party infrastructure.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads and processes external data from PostHog analytics.
  • Ingestion points: Tools such as 'POSTHOG_LIST_AND_FILTER_PROJECT_EVENTS' fetch event names and properties from the PostHog API (SKILL.md).
  • Boundary markers: There are no defined delimiters or instructions to treat fetched event data as untrusted content.
  • Capability inventory: The skill allows the agent to modify feature flags, capture events, and list project configurations (SKILL.md).
  • Sanitization: There is no evidence of filtering or validation to prevent instructional text embedded in event properties from influencing the agent's behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 27, 2026, 10:54 PM