optimize-application

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to read and act on content pulled from public websites (the "website_crawler" via Apify) and KB nodes using commands like branchly-app_list_nodes and branchly-app_read_node and then uses that untrusted, third-party content to drive retrieval, prompt, and tool configuration changes, which could enable indirect prompt injection.