posthog-onboarding

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Step 1: Research (SKILL.md) tells the agent to research a company by name or domain — e.g., "What they build", "job postings, docs, stack" — which requires fetching and interpreting public third-party websites and job postings (untrusted content) that will materially influence subsequent recommendations.