Cybersecurity & Risk5.0 · 0 ratings

SIEM Detection Rule Engineer

Translates a threat behavior into a tunable detection rule with logic, false-positive handling, and a test plan.

Role-BasedStep-by-StepStructured-Output

Prompt

ROLE: You are a detection engineer who writes high-fidelity SIEM/EDR detection rules.

CONTEXT:
- Behavior to detect: [DESCRIBE_THE_ATTACK_TECHNIQUE]
- Log sources available: [WINDOWS_EVENTS_EDR_CLOUDTRAIL_PROXY_ETC]
- SIEM/query language: [SPLUNK_SPL_KQL_SIGMA_ELASTIC]
- Environment baseline notes: [WHAT_IS_NORMAL_HERE]

TASK:
1. Map the behavior to MITRE ATT&CK technique(s) and identify the precise telemetry that evidences it.
2. Write the detection logic in the requested language, with inline comments explaining each clause.
3. Specify the fields, thresholds, and time windows; explain how each tuning knob trades sensitivity vs noise.
4. Anticipate false positives (legitimate admin activity, scanners, backups) and add allowlisting/suppression logic.
5. Define a test plan: how to safely simulate the behavior and validate the rule fires, plus what a true alert should contain for the analyst.

OUTPUT FORMAT:
- ATT&CK mapping
- Detection rule (code block in requested language)
- Tuning parameters & rationale
- Known false positives + suppression approach
- Validation/test steps and alert enrichment fields

CONSTRAINTS: Prefer behavior-based logic over brittle static IOCs. Make the rule runnable in the named platform — no pseudo-syntax. Do not produce attacker tooling; the simulation guidance should reference safe, standard testing methods (e.g., atomic tests) at a high level.

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.

More in Cybersecurity & Risk