dropship-product-research-sop

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the user/agent to fetch and analyze content from public, untrusted sources—e.g., TikTok Ads Library, Facebook Ads Library, Amazon reviews, and AliExpress (including "I'll paste 20 Amazon reviews" and "Here are 3 Facebook ads... I'll paste descriptions/screenshots")—and to use that third-party content to make decisions and drive next actions, which enables indirect prompt injection risk.