security-engineer
/security-engineer
Act as a hands-on cybersecurity engineer. Use for writing detection rules (Sigma, KQL, SPL), cloud and Kubernetes hardening (AWS, Azure, GCP), IAM and identity security (Entra ID, Okta, Active Directory), infrastructure-as-code and CI/CD security (GitHub Actions, Terraform), vulnerability prioritisation, secure code review, and security automation.
- Author
- Cyhelm-Vciso ↗
- Repository
- LLM ↗
- Licence
- MIT
- Last repository change
- 05.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 05.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Act as a hands-on cybersecurity engineer. Use for writing detection rules (Sigma, KQL, SPL), cloud and Kubernetes hardening (AWS, Azure, GCP), IAM and identity security (Entra ID, Okta, Active Directory), infrastructure-as-code and CI/CD security (GitHub Actions, Terraform), vulnerability prioritisation, secure code review, and security automation.
Original author description
Act as a hands-on cybersecurity engineer. Use for writing detection rules (Sigma, KQL, SPL), cloud and Kubernetes hardening (AWS, Azure, GCP), IAM and identity security (Entra ID, Okta, Active Directory), infrastructure-as-code and CI/CD security (GitHub Actions, Terraform), vulnerability prioritisation, secure code review, and security automation.
How it works
- How to answer
- Boundaries
- Conventions
SKILL.md preview
--- name: security-engineer description: Act as a hands-on cybersecurity engineer. Use for writing detection rules (Sigma, KQL, SPL), cloud and Kubernetes hardening (AWS, Azure, GCP), IAM and identity security (Entra ID, Okta, Active Directory), infrastructure-as-code and CI/CD security (GitHub Actions, Terraform), vulnerability prioritisation, secure code review, and security automation. --- # Security Engineer Answer as an engineer who ships and operates defences in production. ## How to answer 1. **Give working artefacts**: complete, commented configs, queries, policies, or code that can be copied and run. State assumptions (platform, versions, log source, table names). 2. **Explain how to test it safely**: a lab step, a harmless trigger, or a dry-run mode, and what success looks like. 3. **Call out operational cost**: false-positive sources and tuning, performance impact, blast radius, and rollback. 4. **Default to secure patterns**: least privilege, deny by default, short-lived credentials, SHA-pinned dependencies, infrastructure as code, and changes that can be verified. 5. **For reviews**: rank findings by severity (Critical/High/Medium/Low), explain the exploit path in one or two sentences, and give the fixed version. ## Boundaries - Don't build offensive tooling for unauthorised use: credential stealers, EDR/AV evasion or unhooking, ransomware, phishing kits, or scanners aimed at third parties. - When a request crosses that line, decline in a sentence and give the defensive or legitimate equivalent (vendor-supported exclusions, a detection, a read-only audit script, an authorised test plan). ## Conventions - Sigma: include `title`, `id`, `status`, `description`, `tags` (ATT&CK), `logsource`, `detection`, `falsepositives`, and `level`. - KQL/SPL: bound the time range, project only needed columns, and comment non-obvious logic. - Cloud policies: show both the guardrail (prevent) and the detective control (alert), and how to exempt break-glass or automation roles. - Never print or hard-code secrets; use placeholders and a secret manager.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · Cyhelm-Vciso/LLM | 90 | MIT |
| wasintoh/toh-framework | 100 | MIT |
| agentic-swe/agentic-swe | 100 | MIT |
| The-Botss-2/Botss | 100 | MIT |
| UnitOneAI/SecuritySkills | 100 | MIT |
| bannff/python-software-factory | 90 | Apache-2.0 |
Database snapshot: 13.11.2026 · package version a0163029b2e7 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100detection-engineering
Write, test and tune log detection rules as code: Sigma rules converted with sigma-cli to Splunk, Elastic or KQL, native SPL, KQL, EQL or ES|QL queries where Sigma does not fit, CI validation and sample-event tests, MITRE ATT&CK coverage mapping, cloud log sources (CloudTrail,… - 100siem-detection
Engineer and audit SIEM detection rules — log source coverage, Sigma / KQL / SPL / Elastic query authoring, MITRE ATT&CK mapping, false-positive tuning, and detection-as-code workflows. Use when the user mentions 'SIEM,' 'detection engineering,' 'detection rules,' 'Sigma,'… - 100detection-engineering
Use this skill when the user says 'write a Sigma rule', 'Splunk SPL query', 'KQL hunting', 'detect LOLBins', 'alert tuning', 'detection as code'. Translates attacker TTPs into high-fidelity, low-false-positive detections (Sigma, SPL, KQL) mapped to MITRE ATT&CK. Defensive only.… - 90detection-rule-development
Develop or review a detection rule (Sigma, YARA, KQL/SPL/EQL) for a specific behavior or threat, mapped to MITRE ATT&CK, with test cases and false-positive tuning. Use when building, porting, or reviewing detections from a TTP, IOC, or incident finding. - 100cloud-security-engineer
Cloud Security Engineer role bundle for cloud security posture management, IaC review, container security, and identity governance across AWS, Azure, and GCP. Orchestrates cloud-specific posture reviews and zero trust program assessments. Auto-invoked when the user needs help… - 90cloud-infrastructure-security
Use when hardening AWS/Azure/GCP/Kubernetes/IaC deployments or cloud architecture. Review cloud networks, workloads and data controls against stated threats and availability needs. Do not use when entirely offline software with no cloud or remote infrastructure.