📦 Train Ticket Ocr — 火车票OCR
v1.0.3一键识别火车票票面全部关键字段，包括出发站、到达站、车次、座位号、票价、乘车日期、身份证号及售票点信息，秒级返回结构化数据，方便报销、归档与行程管理。
0· 136·0 当前·0 累计
by 下载技能包
最后更新
2026/4/16
安全扫描
OpenClaw
安全
high confidenceThe skill's code, README and SKILL.md are consistent with an OCR-for-train-tickets integration that uploads images to the Scnet OCR API and only requires an Scnet API key; nothing in the package indicates hidden or unrelated capability.
评估建议
This skill implements a straightforward client that uploads local ticket images to Scnet's OCR API and returns structured JSON. Before installing or using it: 1) Confirm you trust https://api.scnet.cn and review its privacy/data-retention policy because images can contain sensitive personal data (names, ID numbers, ticket numbers). 2) Provide the SCNET_API_KEY only via a protected configuration method (environment variable or config/.env with 600 permissions) and avoid pasting the key into chat....详细分析 ▾
✓ 用途与能力
Name/description, SKILL.md, scripts/main.py and references/api-docs.md all consistently implement a train-ticket OCR client that uploads a local image and returns structured fields. The requested credential (SCNET_API_KEY) and optional SCNET_API_BASE align with the stated purpose.
ℹ 指令范围
Runtime instructions and the Python script read a local file path and POST the image to https://api.scnet.cn/api/llm/v1/ocr/recognize (default). This is expected for an OCR skill, but it means image data — potentially including names and ID numbers — is transmitted to a third-party service; users should confirm they trust the provider and its data-retention/privacy policies. Minor note: the example command references a .claude/skills/... path which may not match the packaged script location (scripts/main.py); this is a usability inconsistency rather than a security red flag.
✓ 安装机制
No install spec; code is instruction-only plus a small Python script that uses the requests library. Nothing downloads or executes external code beyond normal HTTP requests. The only dependency is requests (pip), which is proportionate to the task.
ℹ 凭证需求
The skill requires a single service credential (SCNET_API_KEY) and an optional SCNET_API_BASE — appropriate for a cloud OCR integration. However, registry metadata at the top of the evaluation incorrectly listed 'Required env vars: none' while SKILL.md and skill.yaml declare SCNET_API_KEY as required; this metadata inconsistency should be resolved before trust decisions. The script reads a config/.env file under its own directory (no system-wide credentials accessed).
✓ 持久化与权限
always:false and no code that modifies other skills or system-wide configuration. The skill runs on-demand and requires the agent to invoke the script; autonomous invocation is permitted (platform default) but not combined with any unusual privileges here.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.32026/3/27
- Added skill.yaml file with metadata and configuration for the skill. - Updated documentation to focus on train ticket OCR only, removing broader general OCR instructions. - Clarified required Python dependencies and included installation instructions for requests library. - Enhanced API key security recommendations, instructing not to paste sensitive info in chat. - Documented API QPS (rate limiting) and provided best practices to avoid triggering limits. - Introduced troubleshooting steps and clarified error handling for API limits and configuration issues.
● 无害
安装命令
点击复制官方npx clawhub@latest install train-ticket-ocr
镜像加速npx clawhub@latest install train-ticket-ocr --registry https://cn.longxiaskill.com