Overview
The risk review assistant is used to answer "what risks are here," privacy policies, data inventories, and compliance assistance, and is suitable for HR, managers, operations, and software to invoke after clarifying business goals, content materials, or analysis targets. It combines inputs such as privacy policy text, pasted privacy policies, data collection statements, permission pop-ups, SDK descriptions, or user notice copy, organizes key context, and outputs summaries, diagnostic conclusions, action recommendations, and reusable deliverables for further execution, review, or delivery.
When to Use
Applicable Scenarios
- Users ask questions such as "what risks are here" and need to quickly break down goals, determine priorities, and form executable results
- HR, managers, operations, and software need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the risk review assistant
- Users have already prepared an uploaded data inventory (uploaded personal information inventory, data flow diagram, SDK inventory, permission table, or compliance self-check form), review priorities (select the direction that needs the highest priority in this privacy policy data map check), and privacy page links (fill in publicly accessible privacy policies, app descriptions, official website notices, or help page links), and want to organize them into executable analysis or optimization results
- Users need to turn risk review assistant-related materials into clear conclusions, priorities, and next-step actions
How to Invoke
Call the AI Skills API directly through the exported Python runner:
Command Example
Basic Invocation
python3 scripts/run.py --params '{}'
Invocation with Common Parameters
python3 scripts/run.py --params '{"dataMapFile":"上传数据清单"}'
Parameter Description
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
dataMapFile |
string | No | - | Upload a personal information inventory, data flow diagram, SDK inventory, permission table, or compliance self-check form |
dataMapCheckFocus |
string | No | 数据项映射 |
Select the direction that needs the highest priority in this privacy policy data map check; optional values:数据项映射、告知缺口、敏感信息、整改清单 |
privacyNoticeLink |
string | No | - | Fill in a publicly accessible privacy policy, app description, official website notice, or help page link; a complete accessible URL is required |
privacyPolicyText |
string | No | - | Paste a privacy policy, data collection statement, permission pop-up, SDK description, or user notice copy |
productDataContext |
string | No | - | Describe the product type, user group, collected data, processing purposes, third-party sharing, and region |
processingActivityNotes |
string | No | - | Supplement sensitive information, minors, cross-border, SDK, withdrawal of consent, and retention period |
For the complete machine-readable parameter structure, see references/form-schema.json。
Parameter Value Reference
This skill currently has no categorical parameters that require an additional lookup table.
Supported Input Formats
This skill currently accepts JSON parameters directly; if a parameter contains a link field, pass a complete, accessible URL.
Example Request
The example parameters below can be passed directly to scripts/run.py, the runner will send them to the AI Skills API.
python3 scripts/run.py --params '{"dataMapFile":"上传数据清单"}'
Equivalent --params JSON：
{
"dataMapFile": "上传数据清单"
}
Example return result
{
"success": true,
"data": {
"message": "示例结果请以技能真实返回结构为准。"
},
"meta": {
"executionTime": 842,
"cached": false
}
}
Deliverables
- Summary, diagnostic conclusions, action recommendations, and reusable deliverables: organize the core results around the user's goals that can be directly read, reviewed, or delivered.
- Interpretation of input materials: combine the uploaded data list (uploaded personal information list, data flow diagram, SDK list, permission table, or compliance self-check form.), inspection focus (select the direction that needs the highest priority in this privacy policy data map inspection.), privacy page link (fill in a publicly accessible privacy policy, App description, official website notice, or help page link.) to extract key context and basis for judgment.
- Next steps: provide priorities, execution suggestions, or a content framework that can be further processed.
Suggestions for using the results
- First determine whether the output answers the user's core questions about the "Risk Review Assistant".
- Then check whether the results cover the summary, diagnostic conclusions, action recommendations, and reusable deliverables, and whether clear next steps are provided.
- If there is little input material, it is recommended to have the user supplement the goals, audience, constraints, or original materials before running.
Preparation before running
AISKILLS_BASE_URL: defaulthttps://ai-skills.aiAISKILLS_API_KEY: required, used for authenticated callsAISKILLS_TENANT_ID: defaultdefault