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。

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.

Type: OpenClaw Skill Name: opensanctions-watchlist Version: 0.3.2 The skill bundle exhibits a major structural discrepancy between its stated purpose (OpenSanctions/KYC compliance) and its actual operational logic, which is almost entirely focused on quantitative stock trading using the ZVT framework. SKILL.md and seed.yaml contain 'Fatal' semantic locks (e.g., SL-01, SL-08) and architectural stages (trading_execution) that govern stock trading and MACD indicators, which are irrelevant to a sanctions watchlist. While no explicit evidence of data exfiltration or malicious execution (like reverse shells) was found, the mismatch suggests either a severely misconfigured bundle or a 'Frankenstein' template that could lead to unpredictable agent behavior when executing financial instructions.