migrate-posthog

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The skill workflow consumes outsider-submitted feature flag definitions and metadata from PostHog via MCP tools (feature-flag-get-all and feature-flag-get-definition), allowing untrusted free text into the agent's context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill contains instructions for executing curl commands that download and run code/telemetry data from remote URLs (https://onboarding.confidence.dev and https://events.eu.confidence.dev), establishing an unknown/suspicious external operational dependency.