posthog-onboarding-lead-research

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (Step 1 "Web searches to run" and Step 5 "Web searches to run") explicitly instructs the agent to fetch and interpret public web content (news, Crunchbase, job postings, etc.), which is untrusted third-party material that directly influences scoring, recommendations, and outreach actions.