SKILLEMALL.ai
GitHub ↗ RU Sign in

BC amlclaw

AI-powered crypto AML compliance toolkit. Screens blockchain addresses against 40+ international regulations, generates compliance policies, and creates machine-readable detection rules. Covers Singapore MAS, Hong Kong SFC, Dubai VARA, FATF, OFAC sanctions. Ships with pre-built rulesets and policies — works out of the box. Use when: screening addresses, generating AML rules, creating compliance policies, investigating crypto transactions, or when user mentions 'AML', 'compliance', 'screen address', 'KYA', 'rules'.

ClawHub Agent Skills author: npc7 v2.0.0 MIT-0 31 files body ≈ 2 011 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

AnalyzerSecuritytype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
B
86/100
safety, quality, tests
Safety 60%
87
Quality 40%
85
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
0
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 · 13

    ✓ No critical or high findings

    Medium and low: 13
    • low Risky intent intent-offensive-security defaults/policies/singapore_mas.md:48
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | **High** | Cybercrime, Obfuscation, Gambling, High-Risk Entities | Hacker/Thief, Ransomware, Phishing, Ponzi, Pig Butchering, Mixers, Privacy Wallet, Unlicensed Gambling, Sanctioned CEX |
    • low Risky intent intent-offensive-security references/dubai/迪拜机构链上风控合规配置指南.md:40
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | **网络犯罪 (Cybercrime)** | 被盗资金 (Hacker/Thief)、勒索软件 (Ransomware)、网络钓鱼 (Phishing)、庞氏骗局 (Ponzi)、杀猪盘 (Pig Butchering)、项目方跑路 (Rug Pull)、蜜罐合约 (Honeypot)、虚假预售 (Fake Presale)、黑/灰产交易 (Black/Grey Industry) | **
    • low Risky intent intent-offensive-security references/fatf/FATF-002-VA-VASP-Guidance-2021.md:297
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      doing so, the Guidance supports the effective implementation of national AML/CFT measures for the regulation and supervision of VASPs (as well as other obliged entities) and the covered VA activities
    • low Risky intent intent-offensive-security references/fatf/FATF-002-VA-VASP-Guidance-2021.md:318
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      individual VASPs operating in the sector and the legal and regulatory approach in the country, taking into account the cross-border, Internet-based nature and global reach of most VA activities. The G
    • low Risky intent intent-offensive-security references/fatf/FATF-002-VA-VASP-Guidance-2021.md:336
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      that VAs are becoming increasingly mainstream for criminal activity more broadly. The majority of VA-related offences highlighted in the report focused on predicate or ML offences, but, criminals also
    • low Risky intent intent-offensive-security references/fatf/FATF-002-VA-VASP-Guidance-2021.md:340
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      noted there has been a large increase in the use of VAs to collect ransomware payments and to commit and launder the proceeds of fraud, and the pace, sophistication, and costs of ransomware attacks wa
      detector
    • low Risky intent intent-offensive-security references/fatf/FATF-002-VA-VASP-Guidance-2021.md:541
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      channels/platforms interact with, or are connected to fiat-based transaction channels/platforms and digital services/platforms; c. The nature and scope of the VA payment channel or system ( e.g. , ope
    • low Risky intent intent-offensive-security references/sanctions/SANC-002-OFAC-Virtual-Currency-Guidance.md:91
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | **Ransomware operators** | Addresses used in ransomware attacks |
    • low Risky intent intent-offensive-security references/sanctions/SANC-002-OFAC-Virtual-Currency-Guidance.md:184
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Ransomware-Related
    • low Risky intent intent-offensive-security references/sanctions/SANC-002-OFAC-Virtual-Currency-Guidance.md:188
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      | **Addresses** | Wallet addresses used in ransomware payments |
      detector
    • low Risky intent intent-offensive-security references/sanctions/SANC-002-OFAC-Virtual-Currency-Guidance.md:189
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | **Operators** | Individuals operating ransomware schemes |
    • low Risky intent intent-offensive-security references/singapore/新加坡DPT持牌机构链上风控合规配置指南.md:13
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      • 网络犯罪 (Cybercrime)：被盗资金 (Hacker/Thief)、勒索软件 (Ransomware)、网络钓鱼 (Phishing)、庞氏骗局 (Ponzi)、杀猪盘 (Pig Butchering)、项目方跑路 (Rug Pull)、蜜罐合约 (Honeypot)、虚假预售 (Fake Presale)。
    • low Risky intent intent-offensive-security references/trustin-labels.md:15
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Cybercrime | 网络犯罪 | Ransomware | 勒索软件 | 高风险 |

    Files scanned: 31. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 58/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 6 mutating operations with no state check
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 56 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2011 tokens

    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
    • -32 of 5 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 519: enough signal without eating the budget
    • +4Structure: 23 headings
    • +3Step-by-step instructions: 56 items
    • +4Has examples (5 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

    External checks

    ClawHub: suspicious
    AMLClaw is a real AML compliance toolkit, but it needs review because it combines sensitive third-party screening, weak API-key handling, automatic local file writes, jurisdiction-specific enforcement defaults, and law-enforcement seizure/spyware reference material.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026