Guidance for making videos with video and editing them with edit_video.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required browser-demo workflow (browser_record on a user-chosen site or app, then analyze_image on the review sheet) makes the agent navigate arbitrary web pages, so outsider-authored page text and images can reach the model only after the agent selects those pages.
siddsachar/row-bot
2327c6c
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.