Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly a disclosed web-API workflow, but its acrylonitrile purpose conflicts with gear-product examples and category IDs while sending engineering data to unauthenticated guest endpoints.
Review this skill before installing. Use it only if you intend to send the design parameters to jixietools.com, and treat returned filename, guest_code, and sheet URLs as private links. The publisher should fix the category ID/product mismatch before users rely on it for acrylonitrile CAD work.
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
curl -s "https://jixietools.com/api/v1/products?category_id=8" | python3 -m json.tool
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
curl -s "https://jixietools.com/api/v1/products?category_id=8" | python3 -m json.tool
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
用户选择后，获取该产品的参数定义：
curl -s "https://jixietools.com/api/v1/products/PRODUCT_ID/start" | python3 -m json.tool
返回结构：
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
curl -s -X POST "https://jixietools.com/api/v1/products/PRODUCT_ID/calculate" \
-H "Content-Type: application/json" \
-d '{"inputs": {"修改的参数名": "新值"}, "filename": "之前保存的filename"}'
The skill’s declared purpose is acrylonitrile-process CAD generation, but the workflow references unrelated gear-transmission products and uses a conflicting category ID. This mismatch can misroute user requests to the wrong external product catalog or design flow, causing unintended data disclosure or incorrect production orders.
The skill explicitly states that production sheets can be created and viewed without authentication, but it does not warn that possession of the returned link or guest code may grant access. Link-based unauthenticated access increases the risk of unauthorized viewing, enumeration, or accidental sharing of potentially sensitive engineering artifacts.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -s -X POST "https://jixietools.com/api/v1/products/PRODUCT_ID/calculate" \
-H "Content-Type: application/json" \
-d '{"inputs": {"有选项的参数名": ""}}'
The skill instructs sending all collected design parameters to an external API without first obtaining explicit user consent or warning about third-party transmission. Users may unknowingly transmit proprietary or sensitive process-design information off-platform.
The incremental-update request sends modified user parameters plus a persistent filename token to an external service. Because the filename ties the request to a prior server-side workbook/session, leakage or misuse of that identifier could expose or alter an existing design state, especially since the workflow emphasizes unauthenticated operation.
curl -s -X POST "https://jixietools.com/api/v1/products/PRODUCT_ID/calculate" \
-H "Content-Type: application/json" \
-d '{"inputs": {"修改的参数名": "新值"}, "filename": "之前保存的filename"}'
The instruction '用中文与用户对话' imposes a specific language for all interactions. Under the policy, forcing a locale or language without user choice is a natural-language policy violation unless it is explicitly justified as region-specific or optional.
No suspicious patterns detected.