cro-methodology

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md and Implementation Guide explicitly instruct the agent to collect and analyze public, user-generated sources (e.g., competitor webpages, reviews, social media, forums and review mining) — see "Customer Research & Objections" and Implementation Guide Step 2 — so the agent is expected to fetch/interpret untrusted third‑party content that can influence test hypotheses and actions.