SKILLEMALL.ai
GitHub ↗ RU Sign in

CB performing-purple-team-atomic-testing

Executes Atomic Red Team tests mapped to MITRE ATT&CK via Invoke-AtomicRedTeam PowerShell, generates ATT&CK Navigator coverage heatmaps, correlates results against Sigma rules, and runs detection validation loops to measure blue team visibility. Use for purple team exercises, atomic test execution, ATT&CK coverage assessment, or detection engineering validation.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 4 files · 1 script body ≈ 9 604 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Executes Atomic Red Team tests mapped to MITRE ATT&CK via Invoke-AtomicRedTeam PowerShell, generates ATT&CK Navigator coverage heatmaps, correlates results…

As a process B 67/100 · Nearly there — weak spots: failures and branches, execution cost, running it twice

ProcedureInfrastructureData and analyticstype 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
83/100
safety, quality, tests
Safety 60%
90
Quality 40%
72
Run on models
none yet
Process rating
B
67/100
Nearly there
Failures and branches w 10
0
Running it twice w 4
30
Execution cost w 6
40
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 10

✓ No critical or high findings

Medium and low: 10
  • low Risky intent intent-offensive-security references/api-reference.md:5
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Parses Atomic Red Team YAML test definitions, correlates execution logs with SIEM detection results, generates MITRE ATT&CK Navigator heatmap layers, computes per-tactic coverage gap analysis, suggest
  • low Risky intent intent-offensive-security references/api-reference.md:11
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | pyyaml | >=6.0 | Parsing Atomic Red Team YAML test definitions |
  • low Risky intent intent-offensive-security references/api-reference.md:55
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | `--atomics-path` | No | Path to Atomic Red Team atomics directory (default: `C:\AtomicRedTeam\atomics`) |
  • low Risky intent intent-offensive-security references/api-reference.md:68
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Parses all Atomic Red Team YAML files (`T*/T*.yaml`) from the atomics directory. Returns a dictionary keyed by technique ID containing technique name, test count, supported platforms, executor types,
  • low Risky intent intent-offensive-security references/api-reference.md:126
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Privilege Escalation | TA0004 | T1548.002, T1134.001, T1068, T1055.001, and 2 more |
  • low Risky intent intent-offensive-security SKILL.md:3
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    description: 'Executes Atomic Red Team tests mapped to MITRE ATT&CK via Invoke-AtomicRedTeam
    quoted
  • low Risky intent intent-offensive-security SKILL.md:50
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Running purple team exercises using Atomic Red Team test library
  • low Risky intent intent-offensive-security SKILL.md:57
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **Do not use** for full-scope red team engagements requiring custom implants or live adversary simulation beyond atomic tests; use Caldera, SCYTHE, or Cobalt Strike for advanced adversary emulation.
  • low Risky intent intent-offensive-security SKILL.md:59
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **DISCLAIMER**: Atomic Red Team tests execute real attack techniques. Run only on systems you own or have explicit written authorization to test. Many tests modify system state, create artifacts, or t
  • low Risky intent intent-offensive-security SKILL.md:65
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Atomic Red Team atomics repository cloned locally

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 9604 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "domain"
  • note frontmatter-key unknown frontmatter key "subdomain"
  • note frontmatter-key unknown frontmatter key "nist_ai_rmf"
  • note frontmatter-key unknown frontmatter key "atlas_techniques"
  • note frontmatter-key unknown frontmatter key "d3fend_techniques"
  • note frontmatter-key unknown frontmatter key "nist_csf"
  • note frontmatter-key unknown frontmatter key "mitre_attack"

Process rating: all ten parameters 67/100

  • 0Failures and branches. Linear process with no failure handling
  • 30Running it twice. 8 mutating operations with no state check
  • 40Execution cost. Instruction body is 9604 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 47 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress

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
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 364: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 47 items
  • +3Output format is stated explicitly
  • +4Has examples (9 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.