Skip to content

AI prompt · Web pentesting · Infrastructure and AD pentesting · Red teaming

Prompt: engagement scoping questionnaire

Prompt that generates the scoping questionnaire to send a client, based on the engagement type (web, infrastructure, red team) and context, with blockers.

By Steven Carrier Published

Works with: Claude, other chat assistants

You are the lead of an offensive security engagement. Write the scoping questionnaire to send to the client before the engagement is priced and planned.

Engagement type: {{engagement_type}}
Client context: {{client_context}}
Information already known: {{known_information}}

Group the questions by theme: objectives and stakes, technical scope, authorisations and system ownership (including hosting providers and third-party suppliers), contacts and escalation procedure, testing windows and production constraints, accounts and access to be provided, data handled and confidentiality, deliverables and debrief.

Rules:
1. do not ask any question whose answer is already in the known information;
2. write short questions that the client can understand without security expertise, one idea per question;
3. adapt the themes to the engagement type (for example: API and roles for a web test, address ranges and segmentation for an infrastructure test, rules of engagement and a restricted response cell for a red team);
4. mark with an asterisk the blocking questions without which the engagement cannot start;
5. finish with the list of documents to request from the client (signed authorisation, architecture diagram, contacts).

Do not assume any authorisation: if a system may belong to a third party, add the question that lets you check.

Replace the highlighted variables before use.

This prompt produces a tailored scoping questionnaire: it avoids sending a generic form and brings out early the points that block an engagement (a hosting provider’s authorisation, a production window, a missing test account). It is useful in pre-sales as well as in kick-off preparation.

Fill in the variables

Variable Example
{{engagement_type}} penetration test of a web application and its API, grey box
{{client_context}} 60-person SaaS vendor, hosted with a cloud provider, new version going live in six weeks
{{known_information}} domain staging.example.org, two application roles, no load testing wanted

A precise engagement type gives a more relevant questionnaire: write "objective-based red team" rather than "audit". The client’s answers then feed the penetration test scoping checklist.

Review the output

  • Remove superfluous questions and reword those that assume technical vocabulary your contact does not have.
  • Check that the blocking points cover written authorisation, the third parties involved (hosting provider, suppliers) and the emergency contact: add them if the model forgets.
  • Adapt the questionnaire to your contractual terms and confidentiality agreement.
  • Keep control of the pricing: the model knows neither your rates nor your workload.
  • Do not paste into the prompt any client information that your engagement agreement does not allow you to share with an AI service; stay at a general level of description.

Sources

Related resources

  • AI skill · Web pentesting · Infrastructure and AD pentesting · Red teaming

    Engagement scoping skill

    Claude Code skill that prepares the scoping of a pentest or Red Team: client questionnaire, missing authorisations, production risks and test windows.

    Published

  • Methodology · Infrastructure and AD pentesting · Red teaming

    Active Directory config review

    Defensive Active Directory review checklist for audits: privileged accounts, krbtgt, delegation, LAPS, legacy protocols, GPOs, ADCS and logging.

    Published

  • Cheatsheet · Infrastructure and AD pentesting · Red teaming

    Active Directory enumeration

    Authenticated AD enumeration for an internal test: domain, accounts, groups, password policy, shares, LDAP queries and BloodHound collection.

    Published

BEAROPS

Need a penetration test?

BEAROPS experts test your applications, infrastructure and cloud, black box or grey box, following OWASP, NIST and ANSSI guidance.