serp-scraper

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 agent to navigate to and render Google search pages (e.g., https://www.google.com/search) and extract SERP content—organic results, featured snippets, People Also Ask, ads, and more—which are untrusted, third-party web content the agent reads and uses as part of its workflow, enabling indirect prompt injection.