post-development

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md) instructs the agent to "discover public routes" and "capture all public pages" using a provided base-url (e.g., /post-dev init --base-url ...), which means the agent will fetch and parse publicly hosted pages whose untrusted, user-generated content could influence SEO, screenshots, personas, ads, and landing-page generation.