wilco-ad-setup

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to call research_products(...) and amazon_keyword_research(...) (Phase 1 and Phase 2) to fetch competitor ASINs, keyword lists, search volumes, ranks and purchase rates from public marketplace data, then directly reads and uses those third-party results to compute wilco_score and drive campaign/bid decisions, which exposes the agent to untrusted external/user-generated content that can materially influence actions.