rstack-content

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and parses live content from the operator's public resolved.sh subdomain (e.g., GET https://{subdomain}.resolved.sh/posts, /courses and ?format=json to read md_content and detect paywall markers) and then uses that untrusted, user-generated page content to decide actions and generate PUT commands (publish/update content and place paywall), so third-party content can directly influence the agent's behavior.