competitor-alternatives

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md Research Process explicitly requires mining and using untrusted public sources ("Review mining: G2, Capterra, TrustRadius" and "Content research: their positioning, their comparison pages, their changelog") and instructs the agent to read and incorporate that third‑party content into competitor profiles and page generation, which could allow indirect prompt injection from user-generated or publicly hosted content.