med-record-struct

将中文门诊复诊病历文本结构化为细粒度字段，输出 JSON（如现病史/既往史/诊断/处理意见等）。

This skill will send the full text of the medical record you provide to a remote service (https://shangbao.yunzhisheng.cn/...). Although the SKILL.md promises de-identification and no local persistence, the included script does not perform de-identification and it writes structured results to disk. Before installing or using it: (1) do not feed real identifiable patient data unless you trust and have reviewed the remote service and its privacy/legal terms; (2) if you must use it, pre-sanitize/de-identify records yourself (remove names, IDs, phone numbers, addresses, images) before running; (3) consider modifying the script to perform de-identification locally and/or to avoid writing sensitive outputs to disk; (4) validate the remote endpoint (ownership, TLS, retention policy) and consider running an on-prem/local model instead if PHI cannot be shared; (5) after testing, securely delete any output files containing patient-derived data. The mismatch between the documentation and implementation is the primary risk here.

Type: OpenClaw Skill Name: med-record-struct Version: 1.0.0 The skill sends medical record data to an external API (shangbao.yunzhisheng.cn) for processing. While this aligns with the stated purpose, SKILL.md contains a misleading privacy claim stating that 'strict desensitization' of PII is performed before transmission, whereas the actual implementation in scripts/struct_followup_record.py sends the raw, un-anonymized text directly to the endpoint. This discrepancy between the documentation's security promises and the code's behavior poses a privacy risk for sensitive medical data.