purple-team-automation
Skill1 starsChanged 3 months agoMITView on GitHub
Purple team automation skill that links offensive emulation (Atomic Red Team, Caldera, Stratus Red Team, Leonidas) with detection validation, telemetry-gap analysis, and continuous control testing. Use to design adversary emulation plans tied to MITRE ATT&CK, execute safe tests in lab or controlled environments, and produce evidence-backed detection coverage reports.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Masriyan/gemini-security-skillsword for word, first seen Oct 25, 2026
Other versions1 project uses a version of this.
Word for word · 1
- Masriyan/gemini-security-skills★ 4100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- ai-redteamSkill
- api-security-automationSkill
- assembly-programmingSkill
- bug-bounty-workflowSkill
- claude-mythos-emulationSkill
- cloud-security-automationSkill
- cybersecurity-partnerSkill
- detection-engineeringSkill
- devsecopsSkill
- exploit-developmentSkill
- forensics-triageSkill
- gemini-tool-orchestratorSkill
- go-programmingSkill
- kubernetes-securitySkill
- malware-reverse-engineeringSkill
- multilingualSkill
- offensive-securitySkill
- osint-recon-automationSkill
- prompt-enhancementSkill
- python-programmingSkill
- smart-contract-auditSkill
- soc-operationsSkill
- threat-intel-fusionSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Run only in environments with written approval, change windows, and rollback owners.
- Distinctive: line 12
No data destruction, no real credential theft, no third-party services targeted.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Purple Team Automation
Authorization Boundary
- Run only in environments with written approval, change windows, and rollback owners.
- Tag every test with a unique
campaign-idfor cleanup and timeline reconstruction. - No data destruction, no real credential theft, no third-party services targeted.
Campaign Workflow
- Pick an adversary or technique set with business relevance; cite ATT&CK IDs and known intrusion sets.
- Draft an emulation plan: prerequisites, steps, expected telemetry, success/fail criteria, cleanup.
- Execute with
invoke-atomicredteam,calderaoperations,stratus, or custom scripts in isolated runners. - Capture telemetry across EDR, Sysmon, cloud audit, network, identity, and SIEM.
- Compare expected vs observed events; flag missing logs, parsing failures, and rule misses.
- File defensive backlog: new detections, tuning, telemetry enablement, and response runbook updates.
Coverage Scoring
Prevented,Alerted,Logged-not-alerted,Missed. Score by technique and by data source.- Track time-to-detect and time-to-contain per test.
- Maintain a heatmap over ATT&CK with last-validated date and confidence.
Output Contract
plans/<campaign>.md: technique list, steps, expectations.runs/<campaign>/: command logs, artifacts, screenshots, raw telemetry.coverage.csv: technique × status × evidence × backlog ticket.report.md: executive coverage, top gaps, prioritized fixes with owners.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.