Quarantining Multimodal Evidence
Use when screenshots, PDFs, images, rendered pages, document previews, or other visual inputs may affect an agent that can click, write, send, or call tools.
Review multimodal evidence, outbound access, trace reuse, assumptions, and boundary changes before agents receive tools or create side effects.
This is a complete workflow library with 3 individual skills. Download the full library or pick the specific skill folder your team needs first.
Some AI tools expect one skill folder per upload. Download the full library when you want the whole workflow, or download an individual skill when you only need one job done.
Use when screenshots, PDFs, images, rendered pages, document previews, or other visual inputs may affect an agent that can click, write, send, or call tools.
Use when an agent workflow requests browser access, web search, package registries, vendor APIs, webhooks, MCP servers, or another outbound network destination.
Use when prompts, tool calls, screenshots, retrieval results, or model outputs may become logs, memory, eval cases, tickets, incident notes, training examples, or vendor telemetry.
Use the public library when the workflow is low-risk, the inputs are already sanitized, and a team member can review the output before it reaches a buyer or customer.
Do deeper review when this workflow touches real tools, data sources, role ownership, approval paths, or customer-facing output.