SKILLEMALL.ai
GitHub ↗ RU Sign in

CC emulating-cloud-attacks-with-stratus-red-team

Install and run Stratus Red Team to detonate granular, MITRE ATT&CK-mapped AWS, Azure, GCP, and Kubernetes attack techniques through their warmup-detonate-revert-cleanup lifecycle, then verify the telemetry they generate. Use to validate that cloud detections (CloudTrail, GuardDuty, Microsoft Sentinel, GCP SCC, Falco) actually fire, or to run a repeatable purple-team exercise generating realistic attacker telemetry.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 5 files · 1 script body ≈ 2 633 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Install and run Stratus Red Team to detonate granular, MITRE ATT&CK-mapped AWS, Azure, GCP, and Kubernetes attack techniques through their…

As a process C 59/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice

AnalyzerAWSGoogle CloudKubernetesAzureSecurityPeople and hiringtype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
88/100
safety, quality, tests
Safety 60%
92
Quality 40%
81
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 8

    ✓ No critical or high findings

    Medium and low: 8
    • low Risky intent intent-offensive-security references/api-reference.md:1
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # Stratus Red Team — Command Reference
    • low Risky intent intent-offensive-security references/api-reference.md:18
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | `stratus version` | Print the Stratus Red Team version |
    • low Risky intent intent-offensive-security references/standards.md:21
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Datadog Stratus Red Team — https://stratus-red-team.cloud
    • low Risky intent intent-offensive-security SKILL.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      description: Install and run Stratus Red Team to detonate granular, MITRE ATT&CK-mapped
    • low Risky intent intent-offensive-security SKILL.md:27
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # Emulating Cloud Attacks with Stratus Red Team
    • low Risky intent intent-offensive-security SKILL.md:29
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      > **Legal Notice:** This skill is for authorized security testing and detection-validation purposes only. Stratus Red Team spins up and modifies real cloud infrastructure in the account whose credenti
      detector
    • low Risky intent intent-offensive-security SKILL.md:33
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Stratus Red Team is an open-source "Atomic Red Team for the cloud," maintained by Datadog. It is a self-contained Go binary that programmatically *detonates* granular, well-documented offensive techni
    • low Risky intent intent-offensive-security SKILL.md:49
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Stratus Red Team binary (Go 1.23+ to build from source, or Homebrew/Docker):

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "domain"
    • note frontmatter-key unknown frontmatter key "subdomain"
    • note frontmatter-key unknown frontmatter key "nist_csf"
    • note frontmatter-key unknown frontmatter key "mitre_attack"

    Process rating: all ten parameters 59/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 30Running it twice. 7 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 28 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2633 tokens
    • 100Progress reporting. Reports progress
    • low 11 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -42 reference files, but SKILL.md never points to them: the model will not open them
    • +2Single-language instructions
    • +3Description length 419: enough signal without eating the budget
    • +4Structure: 21 headings
    • +3Step-by-step instructions: 28 items
    • +4Has examples (11 code blocks)
    • +3All 1 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.