generating-testimonial-quotes

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

• Third-party content exposure detected (high risk: 0.85). The skill explicitly directs the agent to gather and extract testimonials from public, user-generated sources (see "Step 1: Identify Quote Sources" listing Google, G2, Capterra, Trustpilot, social comments, Slack/Discord, etc.), so the agent would read and interpret untrusted third‑party content.