email-campaign

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow clearly shows the agent calling external APIs (e.g., orth api run hunter /v2/domain-search, fiber /v1/company-search, sixtyfour /enrich-lead, brand-dev /v1/brand/retrieve) to fetch public/company/contact data and enrichment that the agent is expected to read and use to personalize outreach and decide follow-up actions, so untrusted third‑party content can materially influence behavior.