readme-to-landing-page

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

• Third-party content exposure detected (high risk: 0.80). The skill's required "Gather Context" step explicitly instructs the agent to check public GitHub metrics ("GitHub stars, forks, download stats, notable users"), which are untrusted, user-generated third‑party data the agent would read and use to shape the rewrite, creating a clear avenue for indirect prompt injection.