Skill 1
Multimodal evidence boundary mapper
Use when screenshots, PDFs, images, browser pages, document previews, emails, tickets, or tool outputs need to become bounded evidence rather than executable instructions.
Back to Skill Library
Agent governance workflow library
Agent boundary control review
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 5 individual skills. Download the full library or pick the specific skill folder your team needs first.
Individual skills in this library
Use one skill at a time, or keep the full workflow together.
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.
Skill 2
Agent egress allowlist reviewer
Use when an agent needs outbound network access, web search, browser access, package registries, vendor APIs, webhooks, or MCP tools.
Skill 3
Agent trace redaction gatekeeper
Use when traces, logs, memory, evals, tickets, incident notes, training examples, or vendor-visible telemetry may contain sensitive workflow details.
Skill 4
Agent assumption register writer
Use when an agent is about to write files, email, publish, deploy, update CRM, call tools, store memory, or make a customer-facing claim from inferred intent.
Skill 5
Agent boundary change reviewer
Use when a model, prompt, tool, data source, egress rule, tracing rule, approval path, or boundary condition changes.
Security fit check
Is the public Agent boundary control review library enough, or does this need deeper review?
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.
Boundary controlAI OperationsSecurityPlatform Owner
Good deeper-review trigger signals
- The workflow touches customer, prospect, CRM, proposal, security, pricing, or campaign data.
- Different teams disagree on the approved source of truth.
- The AI output could become customer-facing, revenue-impacting, or compliance-sensitive.
- You need reusable eval checks before asking more people to use the workflow.