anduoduo-openclaw-skill
AdvisoryAudited by VirusTotal on Mar 27, 2026.
Overview
Type: OpenClaw Skill Name: anduoduo-openclaw-skill Version: 1.1.2 The skill bundle is a comprehensive set of instructions for an AI agent to interact with the Anduoduo cloud security platform's OpenClaw API. It contains strong security guardrails, explicitly instructing the agent to never persist API keys locally, to only use credentials for the official domain (app.anduoduo.net), and to obtain explicit user consent before initiating requests. The bundle includes detailed SOPs, API documentation, and HTML templates (anduoduo_risk_report.html) designed for data visualization. While it instructs the agent to proactively generate reports, this behavior is strictly aligned with the stated purpose of 'data analysis and reporting' and includes instructions to use mock data for examples to prevent sensitive data exposure.
Findings (0)
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.
A simple query about risks may cause the agent to invoke this skill and generate a report file, not just answer in chat.
The skill uses broad trigger language and mandates report generation even when the user did not explicitly ask for a report. This is still related to the stated purpose, but users should know it may add extra actions.
只要用户提到安多多、OpenClaw...就应优先使用本技能...必须生成基于固定模板的 HTML 彩页报告，即使用户没有明确要求模板或图表
Ask the user before generating files or using the fixed report workflow when the request could be answered with text.
If used, the skill could start platform tasks or change account-related state, not only read data.
The documentation includes non-read API actions such as starting scans, exporting reports, and adding cloud accounts. It says they are not the default path, so this is a note rather than a concern, but these actions can affect platform state.
E. 异步任务/扩展能力层 - `POST /scans` - `POST /reports/compliance` - `POST /cloudAccounts/add` ...默认查数不应把这些接口作为主干起点，但可在需要“刷新数据”或“导出正式文件”时作为扩展路径。
Require explicit user confirmation before calling scan, report-export, or cloud-account mutation endpoints; keep default workflows read-only.
The agent can access Anduoduo cloud asset, risk, and compliance information using the user's API key.
The skill requires an Anduoduo API key and uses it to access the official service. The artifacts also include appropriate limits against persistence or sending the key to other domains.
本技能通过系统环境变量 `ANDUODUO_API_KEY` 获取凭据...API 密钥仅用于构建发往安多多官方 API（`https://app.anduoduo.net`）的请求头。
Use a least-privilege API key, confirm each use, and rotate the key if it is ever exposed.
Opening a generated report may contact a third-party CDN and execute remote JavaScript in a page containing risk-report data.
The generated HTML report template loads a third-party JavaScript library from a CDN. This is purpose-aligned for charting, but the remote script runs in the report page and no integrity metadata is shown.
<script src="https://cdn.jsdelivr.net/npm/chart.js@4.4.0/dist/chart.umd.min.js"></script>
Bundle the chart library locally or add Subresource Integrity and clear disclosure for environments that handle sensitive reports.
A generated cloud-risk report could be placed behind an externally accessible link in an unclear storage location.
The skill prioritizes uploading generated deliverables to object storage, but does not specify the storage destination, access controls, link expiration, or a required user approval step before upload. The deliverables may be derived from sensitive cloud asset and risk data.
若任务生成了 HTML、CSV、JSON、ZIP 等文件交付物：1. 先判断是否具备对象存储上传能力；若具备，则优先上传并返回可访问链接
Default to local or direct delivery unless the user explicitly approves upload; specify the storage provider, private ACL, expiration, and redaction rules before sharing.