SKILLEMALL.ai
GitHub ↗ RU Sign in

CB detecting-suspicious-powershell-execution

Hunt for suspicious PowerShell execution (T1059.001) such as encoded commands, download cradles, AMSI bypass, and constrained language mode evasion using EDR telemetry (CrowdStrike, Microsoft Defender for Endpoint), Sysmon, and SIEM queries (Splunk, Elastic). Use when proactively threat hunting, triaging EDR/SIEM alerts, or scoping an incident involving malicious PowerShell activity.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 8 files · 2 scripts body ≈ 691 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Hunt for suspicious PowerShell execution (T1059.001) such as encoded commands, download cradles, AMSI bypass, and constrained language mode evasion using EDR…

As a process B 68/100 · Nearly there — weak spots: failures and branches, running it twice

AnalyzerPeople 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
89/100
safety, quality, tests
Safety 60%
96
Quality 40%
78
Run on models
none yet
Process rating
B
68/100
Nearly there
Failures and branches w 10
0
Running it twice w 4
30
Tools and files w 18
60
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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • low Dangerous commands cmd-execpolicy-bypass references/api-reference.md:35
      Runs PowerShell with execution policy bypassed (documentation of a security skill)
      powershell -ExecutionPolicy Bypass -File script.ps1
      security skill
    • low Risky intent intent-offensive-security references/standards.md:38
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Atomic Red Team Tests: https://github.com/redcanaryco/atomic-red-team
    • low Risky intent intent-offensive-security references/workflows.md:45
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Trace lateral movement and privilege escalation paths
    • low Risky intent intent-offensive-security SKILL.md:90
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      2. **Scenario 2**: IEX download cradle fetching payload from C2 server

    Files scanned: 8. 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 68/100

    • 0Failures and branches. Linear process with no failure handling
    • 30Running it twice. 1 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 21 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 691 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
    • +4Description does not say when NOT to use the skill (false activations)
    • -43 reference files, but SKILL.md never points to them: the model will not open them
    • -32 of 2 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +3Description length 386: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 21 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: 78.