cold-outreach-sequence

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

• Third-party content exposure detected (high risk: 1.00). The skill's "Research First" and workflow steps explicitly require the agent to look up and use content from public third‑party sources (LinkedIn, Twitter/X, company sites, Product Hunt, Crunchbase, job postings) as the hook for Email 1, meaning untrusted/user-generated web content is ingested and can influence the agent's next actions.