opengis-skills
PassAudited by ClawScan on May 13, 2026.
Overview
This is an instruction-only documentation/index skill; it does not install code itself, but some examples can run third-party tools or use service credentials if a user chooses to execute them.
This skill appears safe to install as documentation, but do not let an agent automatically run the included shell commands, remote installers, API calls, email sends, or server/database operations without reviewing the exact command, target environment, credentials, and expected changes.
Publisher note
面向 AI 编程助手的开源 GIS、CAD、C#、AI、IoT 技能集合。覆盖 56 个开源项目，提供一站式技能索引、标签搜索、按需加载指南，让 AI 助手在 GIS/CAD/C# 领域获得更准确的代码生成与问题排查能力。
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If a user or agent runs this command, it can modify the target server by executing whatever the remote install script contains.
The documentation includes a visible one-line remote install script. It is a manual setup example for the documented mail platform, not code automatically run by the skill, but it would execute remote code if copied.
curl -sSL https://www.billionmail.com/install.sh | bash
Only run such setup commands on intended test or server environments after inspecting the script or using a pinned, trusted release path.
If followed blindly, an agent could run local scripts or GIS processing jobs that read or write user data.
The QGIS command reference documents running Processing models or Python scripts. This is expected for a QGIS automation skill, but arbitrary script execution should remain user-approved and scoped.
qgis_process run /path/to/my_script.py -- INPUT=data.shp OUTPUT=result.shp
Approve the exact input files, output paths, plugins, and scripts before allowing an agent to run qgis_process commands.
If a real token is supplied, an agent could perform actions allowed by that token, such as sending email through the configured service.
The documentation includes placeholder API-token usage for a mail-sending API. This is purpose-aligned integration guidance and there is no evidence the skill collects or stores tokens.
-H 'Authorization: Bearer <API_TOKEN>'
Use least-privilege tokens, avoid pasting secrets unless necessary, and require explicit approval before actions that send email or change account/server state.
An agent using these examples could help create or trigger email campaigns if given access to a real server and token.
The BillionMail skill documents bulk/transactional email sending and API calls. This matches the described mail-platform purpose, but public communications are high-impact if automated without review.
"批量营销发送" ... "curl -X POST https://your-server/api/v1/mail/send"
Require user confirmation for recipient lists, message content, sending limits, and compliance settings before allowing any mail-sending action.