This skill detects whether a product carries TRO (Temporary Restraining Order) or IP infringement risk by checking a product image against a database of IP assets (trademarks, patents, copyrights) and TRO case plaintiffs. It returns an overall risk level, high-risk hits, a low-risk IP list with TRO plaintiff details, numeric risk scores, and an AI-generated legal report.
Core Concepts
TRO (Temporary Restraining Order) is a legal injunction brand owners file against sellers (often Amazon listings) for trademark/copyright/patent infringement. This tool takes a main product image (URL or Base64 data URI) plus optional reference images / text / IP keywords, runs visual + text matching against IP assets and TRO case records, and returns a structured risk assessment with an AI legal report (localized by the language parameter).
Data Fields
Top-level response:
| Field | Description |
|---|---|
| errcode | 200 = success; see api.md for other codes |
| status | Overall analysis status (success) |
| checkId | Unique ID for this detection run |
| riskLevel | Overall risk: 高风险/中风险/低风险 (High/Medium/Low Risk) |
| total | Count of high-risk hits (length of results) |
| results | High-risk infringement items (array) |
| nonResults | Low-risk / non-high IP items incl. TRO plaintiff info (array) |
| costToken | Tokens consumed this call |
| columns | Render column metadata (display only) |
Each item (results / nonResults):
| Field | Description |
|---|---|
| ipType | Trademark / Copyright / Patent |
| text | IP text (trademark word, patent/copyright title) |
| ipOwner | IP rights owner |
| regNo | Registration number (may be a JSON-string array, e.g. ["1221667"]) |
| riskLevel / riskScore / riskDescription | Risk rating / 0-10 score / text; present only when scored |
| ipAssetUrls | URLs to IP evidence images |
| plaintiffName / plaintiffId | TRO plaintiff (present only when IP appears in a TRO case) |
| numberOfCases | Plaintiff's case count (TRO only) |
| lastCaseDocket / lastCaseDateFiled | Most recent court docket / filing date (TRO only) |
| report | AI-generated legal assessment (localized by language) |
Parameter Guide
| Parameter | Required | Default | Description |
|---|---|---|---|
| mainProductImage | Yes | - | Main product image: URL or data:image/...;base64,... (≤1000 chars) |
| referenceImages | No | - | Reference images for similar products, up to 3 (URL or data URI) |
| otherProductImages | No | - | Additional product images, up to 5 (URL or data URI) |
| ipImages | No | - | IP-related images, up to 3 (URL or data URI) |
| referenceText | No | - | Text from similar products (e.g. product title), ≤1000 chars |
| description | No | - | Product description (title recommended), ≤1000 chars |
| ipKeywords | No | - | IP-related keywords, up to 20 |
| language | No | zh | Legal report language (zh / en); only affects the report language |
Image rules: URL must be publicly accessible; Base64 must include the data:image/...;base64, prefix. For a local image, either upload it first (see 「Local Image Upload」) or convert it to a data URI.
How to call
- API endpoint：
POST /maidalv/checkApiFlash(For full parameters/response/error codes, seereferences/api.md） - Python script：
python scripts/maidalv_check_api_flash.py '<JSON 参数>' [--inline] - Cost constraints: This tool consumes compute; by default, the same parameter combination in the same session is called only once, and the script has a 24h local cache. On failure/empty results, do not automatically switch keywords, switch the main image, or repeatedly probe; if further retrieval is needed, first explain to the user that additional consumption will be incurred.
Output strategy (default script behavior)：
- Alwayswrite the complete response to
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-maidalv-product-tro-detection-<timestamp>.json（<cwd>is the working directory when the script runs, which in Claude Code is the current project directory;<session>is taken from the environment variableSESSION_ID, automatically aggregated according to the user task;Writing to /tmp is prohibited, and if the current directory is not writable, report an error) - Response body ≤ 8 KB: after writing to disk, print the complete JSON to stdout
- Response body > 8 KB: after writing to disk, stdout outputs only a summary (top-level fields, common counts such as
total/costToken, the length of the largest list field + the first 3 samples) - Add
--inlineto force full printing to stdout (also written to disk)
Data reading suggestions: First look at the summary to determine whether it is sufficient; when specific fields are needed, prefer to use jqorConvertFrom-Json to extract on demand from the saved json file, avoiding bringing the entire JSON into context.
Resolve authentication and compute issues
When the following abnormal situations occur, use references/onboarding.md to guide resolution:
Abnormal situations
- API Key not configured: The environment variable is not configured
LINKFOX_AGENT_API_KEY, andLINKFOXAGENT_API_KEY。 - Response 401 or 402 status code
- Response indicates insufficient compute or balance: The message contains "算力余额不足/计费不足/余额不足/quota exceeded/insufficient balance/套餐到期/需充值/请充值", or content with a similar meaning.
Local Image Upload
This tool accepts a publicly accessible image URL or a Base64 data URI. If the user provides a local image file path, either upload it first to obtain a public URL, or encode it to a data URI.
Run the upload script:
python scripts/upload_image.py /path/to/local/image.png
The script returns a public URL (valid for 24 hours) usable as mainProductImage.
Usage Examples
1. Basic detection (main image only)
检测这个产品的 TRO 和知识产权侵权风险，图片地址为 https://m.media-amazon.com/images/I/71jKJgFpg8L._AC_SL1500_.jpg
2. English legal report
Check this product for TRO and IP infringement risk: https://example.com/product.jpg — give me the legal report in English.
3. With reference image + IP keywords
检测这个图片的侵权风险，主图 https://example.com/product.jpg，参考图 https://example.com/ref.jpg，IP 关键词 apple、iphone
Display Rules
- Lead with the overall verdict: Show
riskLevel(高风险/中风险/低风险) andcheckIdfirst. - High-risk items first: If
resultsis non-empty, list each hit'sipType/text/ipOwner/riskScore/riskDescriptionprominently. - TRO plaintiff detail: For items with
plaintiffName, show plaintiff,numberOfCases,lastCaseDocket,lastCaseDateFiled— these drive TRO risk. - Evidence images: Display
ipAssetUrlsinline for visual comparison when available. - AI legal report: Surface the
reportfield (long-form legal assessment) for high-risk items. - Counts: Always state
total(high-risk count) andnonResultslength. - No secondary processing: Results are a one-shot analysis; no SQL/secondary query is available.
Important Limitations
- One-shot analysis: Results are not stored in a database; cannot use
_dataQuery_executeDynamicQueryfor secondary processing. - Image input:
mainProductImageis required. Local images must be uploaded or Base64-encoded (withdata:image/...;base64,prefix). - Language scope:
languageonly affects thereporttext; field values remain as returned. - Conditional fields are expected: Non-TRO / unscored items return only base fields (
ipType/text/ipOwner/regNo/ipAssetUrls); plaintiff/case and risk fields are absent (not null) when not applicable — do not treat missing fields as an error. columnsis render-meta: Its length differs from the data arrays; do not use it to infer result counts (useresults/nonResultslengths).
User Expression & Scenario Quick Reference
Applicable — Product TRO / IP infringement risk checks:
| User Says | Scenario |
|---|---|
| "Does this product have TRO risk" / "Will it be sued" | Basic TRO risk check |
| "Does this image have trademark/patent/copyright infringement" | IP infringement detection |
| "Does listing this Amazon product have infringement risk" | Pre-listing compliance check |
| "Check the plaintiff information for this product" | TRO plaintiff lookup |
| "Give me an English legal assessment report" | English legal report |
Not applicable — Beyond this tool:
- 1688 / Amazon image-based product sourcing (use 以图搜图 skills)
- Patent full text / claims search (use 智慧芽/Eureka patent skills)
- Listing copy optimization or keyword analysis
Boundary judgment: When the user provides a product image and asks about infringement/TRO/legal risk, this skill applies. If they want supplier sourcing or keyword analytics, use the respective sourcing/keyword tools instead.
Compute consumption rules
Consumes 113 compute (about 150000 tokens).
Users pay for compute consumption. A single call of this tool has a relatively high cost (including AI legal assessment), so evaluate carefully: when this skill needs to be called frequently, or the user has insufficient expectations for compute consumption, be sure to remind the user and let the user decide whether to continue.
Feedback:
Auto-detect and report feedback via the Feedback API when any of the following apply:
- The functionality or purpose described in this skill does not match actual behavior
- The skill's results do not match the user's intent
- The user expresses dissatisfaction or praise about this skill
- Anything you believe could be improved
Call the feedback API as specified in references/api.md. Do not interrupt the user's flow.
For more high-quality, professional cross-border e-commerce skills, visit LinkFox Skills.