NEW

Start with the pressure: sales, launch, abuse, agents, data, or guardrails

Agent security

Agentic Workflow Security Packet

A bounded agent: known tools, permissions, approvals, rollback, and a hardening backlog.

The first deliverable is a decision package: what is in scope, what is required, what is blocked, and what can proceed.

No production testing, adversarial activity, access to secrets, or customer-data processing happens without explicit authorization and the right agreement path. Do not enter secrets or credentials here.

What to gather for this packet

Needed: Agent/tool inventory · Permissions & credentials model · Approval & rollback paths · Logs/audit coverage

Helpful: Agent framework · Connected SaaS/cloud · Known abuse concerns

Bring names and high-level descriptions only — exact targets, accounts, and credentials are shared later through a secure channel.

Engagement

Readiness inputs

Deliverables you want

Packet modules

  • Scope BriefWhat is in scope, what decision is being made, and what success looks like.
  • Authorization StatementConfirmation the org owns, controls, or is authorized to assess the targets.
  • Evidence Handling PlanWhere evidence is stored, redaction, retention, and deletion.
  • Contract RequirementsThe required and conditional agreements for this engagement.
  • Draft SOW InputsScope, window, deliverables, and acceptance inputs for the SOW.
  • Open QuestionsWhat is still required before a scoping call or private offer.
  • Follow-On RecommendationsNatural next services once this engagement completes.
  • Target InventoryThe named systems, endpoints, repos, accounts, or surfaces in scope.
  • AI / Agent BoundaryModels, tools, actions, approvals, and rollback paths in scope.
  • Access PlanHow access and test accounts are provisioned through a secure channel.
  • Allowed / Prohibited TechniquesWhich techniques are authorized and which are prohibited by default.
  • Deliverables PlanThe artifacts the buyer will receive and in what format.

Agentic Workflow Security Packet — preview

Agent security

Scope Brief

  • Organization: To be specified during scoping
  • Decision: A bounded agent: known tools, permissions, approvals, rollback, and a hardening backlog.
  • Driver: Agents, tools, credentials, workflows, approvals, and actions have unclear blast radius.

Authorization Statement

  • Not yet confirmed — required before any access or testing.

Evidence Handling Plan

  • Evidence stored in an access-controlled encrypted store; redaction; agreed retention + deletion.

Contract Requirements

  • Mutual NDA — Required for this engagement.
  • Evidence Handling Policy — Required for this engagement.
  • Statement of Work Template — Required for this engagement.
  • Assessment Terms Addendum — Required for this engagement.

Draft SOW Inputs

  • Engagement: Agentic Workflow Security Packet
  • Deliverables: 7 selected
  • Budget category: Platform engineering / security engineering / AppSec / AI program

Open Questions

  • Authorization (own / control / explicitly authorized to assess the targets)
  • Target inventory (named systems/endpoints in scope)
  • Agent boundary (tools, actions, approvals, rollback)
  • Access plan (how access and test accounts are provisioned securely)

Follow-On Recommendations

  • ai red team adversarial testing
  • secure ai sdlc
  • guardrails evals review

Target Inventory

  • No named targets yet — required before testing.

AI / Agent Boundary

  • Agent boundary needed.

Access Plan

  • Access plan needed — secure-channel provisioning, no public credentials.

Allowed / Prohibited Techniques

  • Which techniques are authorized and which are prohibited by default.

Deliverables Plan

  • Agent Authority Graph
  • Tool Permission Matrix
  • Credential Boundary Map
  • Approval / Rollback Plan
  • Abuse-Path Findings
  • Logging and Evidence Requirements
  • Hardening Backlog

Onboarding

Move four tracks in parallel

We put legal, finance, procurement, and technical scoping on parallel rails so the work can start without waiting on every internal process sequentially.

Technical Scoping

Output: Draft Launch Review Plan

  • architecture
  • demo/staging
  • prompts
  • RAG
  • agents/tools
  • authz
  • logs/evals
  • test boundaries

Legal

Output: NDA + Scoping Authorization

  • mutual NDA
  • data handling
  • authorized testing boundaries
  • confidentiality
  • work-product terms

Finance / Procurement

Output: Procurement Packet

  • vendor profile
  • tax/payment details
  • budget category
  • fixed-fee quote path
  • invoice terms
  • onboarding answers

Internal Approval

Output: Approval Memo

  • why now
  • business pressure
  • risk if delayed
  • expected deliverables
  • timeline
  • decision needed

Output

Your output: a clear, measurable prescription.

SCOPE delivers a one-page engagement plan you can share and act on immediately.

  • Situation & core problem
  • Desired outcome & success criteria
  • Key risks & assumptions
  • Recommended path(s)
  • Effort, timing & impact
  • Open questions & next step

SCOPE Prescription

Situation

Criteria

Recommended path

Next step

Export as markdown ↗