SKILLEMALL.ai
GitHub ↗ RU Sign in

CC analyzing-powershell-empire-artifacts

Detect PowerShell Empire post-exploitation framework artifacts in Windows Script Block Logging (Event ID 4104) and Module Logging (Event ID 4103), including the default launcher string, Base64-encoded WebClient/FromBase64String payloads, known module invocations (Invoke-Mimikatz, Invoke-Kerberoast), and staging URL patterns. Use when hunting for or confirming Empire C2 activity in Windows event logs.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 4 files · 1 script body ≈ 460 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Detect PowerShell Empire post-exploitation framework artifacts in Windows Script Block Logging (Event ID 4104) and Module Logging (Event ID 4103), including…

As a process C 64/100 · Has gaps — weak spots: when it triggers, failures and branches

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
88/100
safety, quality, tests
Safety 60%
97
Quality 40%
74
Run on models
none yet
Process rating
C
64/100
Has gaps
Failures and branches w 10
0
When it triggers w 12
20
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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • low Risky intent intent-offensive-security references/api-reference.md:60
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | `Invoke-Mimikatz` | T1003.001 | Credential dumping via Mimikatz |
    • low Risky intent intent-offensive-security references/api-reference.md:64
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | `Invoke-DCOM` | T1021.003 | Lateral movement via DCOM |
    • low Risky intent intent-offensive-security references/api-reference.md:65
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | `Invoke-SMBExec` | T1021.002 | SMB-based lateral movement |

    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_ai_rmf"
    • note frontmatter-key unknown frontmatter key "nist_csf"
    • note frontmatter-key unknown frontmatter key "mitre_attack"

    Process rating: all ten parameters 64/100

    • 0Failures and branches. Linear process with no failure handling
    • 20When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 12 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 460 tokens
    • 100Running it twice. No mutating operations
    • 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)
    • +4No input/output examples
    • -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
    • +3Description length 403: enough signal without eating the budget
    • +4Structure: 6 headings
    • +3Step-by-step instructions: 12 items
    • +3Output format is stated explicitly
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.