Opensanctions Watchlist

OpenSanctions 黑名单合规筛查：国际制裁名单、PEP（政要）、高风险人物数据的 抓取、去重、匹配与版本归档。适用于 KYC 和 AML 尽调。

Security Scan

The skill claims to be a sanctions/PEP watchlist but its runtime instructions and bundled artifacts mix unrelated trading/backtest (ZVT/MACD) requirements and preconditions, and the declared requirements (none) do not match what the SKILL.md asks the agent to read or run.

Purpose & Capability

Name/description advertise OpenSanctions-style sanctions/PEP screening for KYC/AML, but SKILL.md and companion files contain many trading/backtest elements (ZVT, MACD parameters, trading semantic locks, 'trading_execution' in pipeline and human_summary focused on A-share quant flows). That mismatch suggests the bundle was merged or compiled with unrelated blueprints; the extra trading scope does not belong to a pure sanctions watchlist.

Instruction Scope

Although instruction-only (no code), SKILL.md and seed.yaml instruct the agent to reload seed.yaml, run preconditions that execute python commands, check ZVT_HOME, run zvt recorders, and possibly install packages (pip install zvt). These instructions reference filesystem paths, run shell/python commands, and require re-reading bundled files — actions beyond simple read-only sanctions lookups and not reflected in the declared requirements.

Install Mechanism

No install spec or binaries are declared (lowest install risk). However seed.yaml's execution_protocol mentions install recipes and preconditions that instruct pip installs and zvt init commands; the skill bundle itself contains large data (seed.yaml) that the agent is told to re-read. Lack of an explicit install spec is inconsistent with those instructions.

Credentials

Registry metadata lists no required env vars/credentials, yet runtime docs reference environment variables (ZVT_HOME) and ask the user to choose data providers (some of which require accounts/keys: joinquant, qmt). The skill may prompt for or rely on external credentials at runtime despite not declaring them up-front.

Persistence & Privilege

always:false and no special privileges are requested. Still, instructions include commands that create/modify user directories (~/.zvt), run pip installs, and require reloading seed.yaml; these can write to the host filesystem and install packages if followed, so exercise caution even though the skill isn't marked always:true.

What to consider before installing

This bundle is internally inconsistent: it claims to be a sanctions/PEP watchlist but contains trading/backtest content and runtime steps that reference ZVT and shell/python commands. Before installing or invoking it: 1) Ask the publisher/source — where did this come from? 2) Inspect seed.yaml and SKILL.md yourself (they are bundled) to confirm intended behavior. 3) Do not run the included precondition commands (pip install zvt, zvt.init_dirs, or python3 -m zvt.*) on a production machine; use an isolated sandbox if you want to test. 4) Expect the skill to ask for external data-provider credentials at runtime even though none are declared — do not enter secrets until you verify necessity. 5) If you only need sanctions/PEP lookups, prefer a simpler, provenance-clear skill (or official OpenSanctions integrations) rather than this mixed bundle.

制裁名单筛查 (opensanctions-watchlist)

国际制裁名单 + PEP（政要）+ 高风险人物实时筛查——合规 KYC/AML 场景必备。

Pipeline

data_collection -> data_storage -> factor_computation -> target_selection -> trading_execution -> visualization

Top Use Cases (60 total)

Dataset Crawling (ETL) (UC-101)

Automates the extraction, transformation, and loading of data from external sources into the OpenSanctions data store with optional validation and dat Triggers: crawl, extract, load

Wikidata Updates Review (UC-103)

Interactively reviews and applies Wikidata updates to OpenSanctions datasets, allowing manual curation of proposed entity matches Triggers: wikidata, update, review

Database Statement Loading (UC-104)

Loads dataset statements from the archive into a SQL database for querying and analysis, with configurable batch sizes Triggers: load, database, sql

For all 60 use cases, see references/USE_CASES.md.

Execute trigger: When user intent matches intent_router.uc_entries[].positive_terms AND user uses action verb (run/execute/跑/执行/backtest/fetch/collect)

What I'll Ask You

• Target market: A-share (default), HK, or crypto? (US stocks in ZVT are half-baked — stockus_nasdaq_AAPL exists but coverage is thin)
• Data source / provider: eastmoney (free, no account), joinquant (account+paid), baostock (free, good history), akshare, or qmt (broker)?
• Strategy type: MACD golden-cross, MA crossover, volume breakout, fundamental screen, or custom factor?
• Time range: start_timestamp and end_timestamp for backtest period
• Target entity IDs: specific stocks (stock_sh_600000) or index components (SZ1000)?

Semantic Locks (Fatal)

ID	Rule	On Violation
SL-01	Execute sell orders before buy orders in every trading cycle	halt
SL-02	Trading signals MUST use next-bar execution (no look-ahead)	halt
SL-03	Entity IDs MUST follow format entity_type_exchange_code	halt
SL-04	DataFrame index MUST be MultiIndex (entity_id, timestamp)	halt
SL-05	TradingSignal MUST have EXACTLY ONE of: position_pct, order_money, order_amount	halt
SL-06	filter_result column semantics: True=BUY, False=SELL, None/NaN=NO ACTION	halt
SL-07	Transformer MUST run BEFORE Accumulator in factor pipeline	halt
SL-08	MACD parameters locked: fast=12, slow=26, signal=9	halt

Full lock definitions: references/LOCKS.md

Top Anti-Patterns (15 total)

• AP-REGTECH-001: Missing attribute initialization on data structures
• AP-REGTECH-002: Self-loops in transaction graphs violate domain rules
• AP-REGTECH-003: Unvalidated floating-point inputs cause runtime crashes

All 15 anti-patterns: references/ANTI_PATTERNS.md

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-071. Evidence verify ratio = 26.8% and audit fail total = 35. Generated results may have uncaptured requirement gaps. Verify critical decisions against source files (LATEST.yaml / LATEST.jsonl).

Reference Files

File	Contents	When to Load
references/seed.yaml	V6+ 全量权威 (source-of-truth)	有行为/决策争议时必读
references/ANTI_PATTERNS.md	15 条跨项目反模式	开始实现前
references/WISDOM.md	跨项目精华借鉴	架构决策时
references/CONSTRAINTS.md	domain + fatal 约束	规则冲突时
references/USE_CASES.md	全量 KUC-* 业务场景	需要完整示例时
references/LOCKS.md	SL-* + preconditions + hints	生成回测/交易代码前
references/COMPONENTS.md	AST 组件地图（按 module 拆分）	查 API 时

---

Compiled by Doramagic crystal-compilation-v6.1 from finance-bp-071 blueprint at 2026-04-22T13:00:25.342470+00:00. See human_summary.md for non-technical overview.