Skip to content

AI prompt · Red teaming

Prompt: mapping a timeline to MITRE ATT&CK

Prompt that maps the actions of a Red Team or incident timeline to MITRE ATT&CK tactics and techniques, with justification and a confidence level.

By Steven Carrier Published

Works with: Claude, other chat assistants

You are a cybersecurity analyst who knows the MITRE ATT&CK framework (Enterprise). Map each action in the timeline below to an ATT&CK tactic and technique.

Context: {{context}}
Timeline of observed actions: {{timeline}}

Answer as a table, one row per action, with these columns:
- timestamp or action number;
- observed action, restated as one factual sentence;
- ATT&CK tactic;
- technique or sub-technique (name and ID, for example T1566.001);
- justification: the element of the action that supports this mapping;
- confidence: high, medium or low.

Rules:
1. map only what the action shows; if it is ambiguous, propose several candidate techniques and set the confidence to low;
2. flag uncertain mappings clearly in a separate section, with the information that would settle them;
3. do not invent any ID: if you are not certain of an ID, write it in square brackets with the note "to verify";
4. finish with a summary of the tactics covered and the tactics with no observation, without concluding that these did not take place.

Replace the highlighted variables before use.

This prompt maps the actions of a Red Team exercise or an incident to the MITRE ATT&CK framework, for the report, the debrief with the SOC or the measurement of detection coverage. It saves time on sorting, not on validation: the final mapping remains an analyst’s judgement.

Fill in the variables

Variable Example
{{context}} authorised four-week Red Team exercise on a Windows and Active Directory network, scenario "compromise of a user workstation"
{{timeline}} 09:12 simulated phishing email opened by a pilot user; 09:40 attachment executed on the workstation; 11:05 LDAP query for the list of domain administrators

Provide timestamped facts (logs, engagement notes), not interpretations: the more precise the action, the more reliable the mapping. For the structure of the deliverable, see the pentest report skill.

Review the output

  • Check every ID, technique name and tactic on attack.mitre.org: the framework changes with each version and a model confuses or invents IDs.
  • State the ATT&CK version used in the report, so the mapping remains readable later.
  • Examine the low-confidence rows and the uncertain mappings section first.
  • A tactic with no observation proves nothing: it may reflect missing logging or scope.
  • Do not paste into the prompt any client information (hostnames, accounts, IP addresses) that your engagement agreement does not allow you to share with an AI service.

Sources

Related resources

  • 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

  • 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

BEAROPS

Ready for a red team exercise?

BEAROPS runs red team exercises lasting one to six months, built on MITRE ATT&CK, to put your detection and response to the test.