{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/8f146bce803741429bfe62ac830e2a66\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/8f146bce803741429bfe62ac830e2a66-bc910bf7525f123c.gif","duration":250.025,"title":"Automated Security Checks with Make AI Agent","description":"This Loom demonstrates using a Make AI agent to run automated security vulnerability testing on scenario blueprints and store results in Notion. The agent reads scenario inputs including a scenario ID and blueprint, then checks for issues such as prompt injection by attempting prompt injection during the run, and it also evaluates other findings like invalid webhook acceptance and downstream email recipient problems. A scenario without a hook URL runs every 15 minutes, while one with a hook URL triggers the automation and produces a final report in about 10 seconds, completed around 11:52. The results are summarized into Notion with evidence, payloads, impact, recommendations, and guidance on mediation priorities and overall security posture."}