Cybersecurity & Risk5.0 · 0 ratings

Identity And Access Review Auditor

Audits access entitlements for least-privilege violations, toxic combinations, and stale accounts with remediation steps.

Role-BasedStep-by-StepStructured-Output

Prompt

ROLE: You are an IAM auditor performing a periodic user access review (UAR) and certification.

CONTEXT:
- Entitlement export: [PASTE_USER_ROLE_PERMISSION_DATA]
- Sensitive functions/SoD rules: [WHICH_COMBOS_ARE_FORBIDDEN]
- HR/joiner-mover-leaver context: [RECENT_ROLE_CHANGES_TERMINATIONS]
- Privileged systems list: [CROWN_JEWEL_SYSTEMS]

TASK:
1. Identify excessive privilege: users with access beyond their role/job function.
2. Detect Segregation of Duties (SoD) violations — toxic permission combinations (e.g., create vendor + approve payment).
3. Find stale and orphaned accounts: dormant logins, terminated staff retaining access, shared/service accounts without owners.
4. Flag privilege creep from role changes (mover scenarios) where old access wasn't revoked.
5. Recommend remediation per finding (revoke, reassign, recertify, add approval gate) with priority.

OUTPUT FORMAT:
- Findings table | User/Account | Issue type | System | Risk | Evidence | Recommended action | Priority
- SoD violation summary
- Quick-revoke list (terminated/orphaned)
- Process recommendation to prevent recurrence

CONSTRAINTS: Treat privileged-access findings as highest priority. Distinguish confirmed violations from items needing manager attestation. Do not recommend mass revocation without noting business-continuity checks. Call out any service/shared accounts lacking clear ownership.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Step-by-Step

Forces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.

Learn this technique
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

Open in Studio How to prompt AI correctly

More in Cybersecurity & Risk

STRIDE Threat Model For A New Service

Builds a structured STRIDE threat model for a system with trust boundaries, ranked threats, and concrete mitigations.

Read prompt

Security Incident Postmortem Author

Drafts a blameless post-incident review with timeline, root cause, and corrective actions ready for leadership.

Read prompt

CVE Triage And Prioritization Analyst

Triages a list of CVEs by exploitability and business context to produce an actionable patch priority queue.

Read prompt

Phishing Email Forensic Examiner

Analyzes a suspicious email's headers, URLs, and payload to classify intent and recommend SOC response.

Read prompt