SKILLEMALL.ai
GitHub ↗ RU Sign in

CB executing-red-team-exercise

Run a stealthy, MITRE ATT&CK-mapped adversary emulation against an organization's people, processes, and technology, using C2 infrastructure (Cobalt Strike, Sliver, Brute Ratel, Mythic) through the full attack lifecycle to test SOC detection and response rather than just find vulnerabilities. Use when executing a full-scope red team exercise, adversary simulation/emulation, or a regulatory exercise (TIBER-EU, CBEST, AASE, iCAST) with executive authorization and a signed Rules of Engagement already in place.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 4 files · 1 script body ≈ 3 025 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Run a stealthy, MITRE ATT&CK-mapped adversary emulation against an organization's people, processes, and technology, using C2 infrastructure (Cobalt Strike…

As a process B 65/100 · Nearly there — weak spots: failures and branches, running it twice

ProcedureSecurityInfrastructureData 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
89/100
safety, quality, tests
Safety 60%
94
Quality 40%
82
Run on models
none yet
Process rating
B
65/100
Nearly there
Failures and branches w 10
0
Running it twice w 4
30
When it triggers w 12
50
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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • low Risky intent intent-offensive-security references/api-reference.md:1
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # API Reference: Red Team Exercise Agent
    • low Risky intent intent-offensive-security SKILL.md:6
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      than just find vulnerabilities. Use when executing a full-scope red team exercise, adversary
    • low Risky intent intent-offensive-security SKILL.md:40
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # Executing Red Team Exercise
    • low Risky intent intent-offensive-security SKILL.md:47
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - Evaluating the organization's security posture against specific threat actors (nation-state, ransomware groups, insider threats)
      detector
    • low Risky intent intent-offensive-security SKILL.md:55
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Red team command and control (C2) infrastructure: primary and backup C2 channels with domain fronting or redirectors
    • low Risky intent intent-offensive-security SKILL.md:71
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      - **Objective definition**: Define measurable objectives such as "Access customer financial data from the core banking system" or "Demonstrate ability to deploy ransomware across the domain"
      quoted

    Files scanned: 4. 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 "d3fend_techniques"
    • note frontmatter-key unknown frontmatter key "nist_csf"
    • note frontmatter-key unknown frontmatter key "mitre_attack"

    Process rating: all ten parameters 65/100

    • 0Failures and branches. Linear process with no failure handling
    • 30Running it twice. 14 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 62 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3025 tokens
    • 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 512: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 62 items
    • +3Output format is stated explicitly
    • +4Has examples (1 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.