Guidance for using webcam, screen capture, and image analysis.
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 workflow reads web pages via the browser tool (`source='browser'`), which allows outsider-authored content to be ingested into the agent.
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.