Turn a threat report into Sigma detection rules
Extracts behaviors from a threat report, maps them to MITRE ATT&CK, and writes tuned Sigma rules with test notes.
The prompt
Turn this threat report into Sigma detection rules for my environment.
Threat report or advisory: [PASTE the text, or a summary with behaviors and indicators]
Log sources I have: [e.g. "Sysmon", "Windows Security event logs", "PowerShell script block logging", "EDR telemetry", "Linux auditd"]
SIEM or backend: [e.g. "Splunk", "Microsoft Sentinel", "Elastic"]
Noise tolerance: [low / medium / high]
Steps:
1. Extract TTPs: list each attacker behavior the report describes, mapped to a MITRE ATT&CK technique ID. Include only what the report supports; mark weak inferences [INFERRED].
2. Prioritize behaviors over indicators. Hashes, IPs, and domains change quickly; process chains, command-line patterns, registry changes, and parent-child relationships last longer. List atomic indicators separately.
3. Write one Sigma rule per behavior in valid YAML with: title, id (placeholder UUID), status: experimental, description, references, tags (attack.tXXXX), logsource (product, category or service), detection with named selections and a condition, falsepositives, and level.
4. Tune: for each rule, list likely false positives in a normal enterprise, suggest filters, and note which log source or audit setting must be enabled for it to fire.
5. Test: describe a safe way to validate each rule in a lab (e.g. a matching Atomic Red Team test, marked [VERIFY]).
Return: a TTP table (Behavior | ATT&CK ID | Evidence in report | Log source), the Sigma rules in YAML code blocks, then tuning and test notes.
Don't invent event IDs, field names, or ATT&CK mappings; mark anything uncertain [CHECK]. Test rules outside production before deploying them.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Software Development prompts
What to fill in
- PASTE the text, or a summary with behaviors and indicators
- e.g. "Splunk", "Microsoft Sentinel", "Elastic"
- low / medium / high
- INFERRED
- CHECK
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Diagnose slow launches and API cold starts in my mobile appA codebase-specific diagnosis of startup time, serverless cold starts, and network waste, with fixes ranked by impact on perceived speed.
- Set up experiment tracking for a machine learning training runStep-by-step setup to log metrics, hyperparameters, and artifacts from your training script, locally or on a cluster.
- Diagnose and fix a flaky testWorks out why a test passes and fails intermittently, how to reproduce it, and how to fix the cause rather than adding retries.
- Design consistent API error responses developers can act onTurns unhelpful API errors into a consistent format with clear codes, statuses, and messages that tell callers exactly what to fix.