competitive-landing-page

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly requires fetching and verifying real review quotes and competitor data from public user-review platforms (G2, Capterra, TrustRadius) and competitor websites/SVGs as part of Act 2 (Research & Brief) and Act 1 (Product Identity), so the agent will ingest and act on untrusted, user-generated third‑party content.