Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward tank CAD workflow that uses a disclosed external API, but users should know their engineering inputs and generated sheet link leave the local environment.
Install only if you are comfortable sending tank design parameters to jixietools.com and receiving an unauthenticated guest link for the generated production sheet. Avoid entering proprietary or confidential engineering data unless that external service is approved for your use.
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
用 curl 获取储罐列表：
curl -s "https://jixietools.com/api/v1/products?category_id=9" | python3 -m json.tool
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
用 curl 获取储罐列表:
curl -s "https://jixietools.com/api/v1/products?category_id=9" | 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
返回包含 input_params、output_params、debug_params、coefficient_params 四类参数。
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": {"参数名": ""}}'
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": {"参数名": ""}}'
The skill can create guest production sheets without authentication and returns a public guest code/URL, but it does not warn the user that this may create an externally accessible artifact. If the link is guessed, leaked, logged, or shared inadvertently, sensitive design specifications and output files could be exposed.
The trigger list includes broad everyday terms like 'tank' and '做一个储罐', which can cause the skill to activate in contexts where the user did not clearly intend to send engineering data to this external workflow. That increases the chance of unintended data collection and transmission to the third-party API.
The skill instructs collection of detailed user-provided design parameters and later submission to a remote API, but it does not warn the user beforehand that their data will be transmitted off-platform. This undermines informed consent and can expose proprietary engineering or process data to a third party.
This step explicitly sends user-supplied engineering parameters to an external service during calculate/pre-calculate operations. In this skill's context, those values may include proprietary design, process, or operational data, so the transmission is security-relevant even if intended functionality depends on it.
curl -s -X POST "https://jixietools.com/api/v1/products/PRODUCT_ID/calculate" \
-H "Content-Type: application/json" \
-d '{"inputs": {"参数名": ""}}'
The instruction “用中文与用户对话” imposes a specific language requirement unconditionally. This is a natural-language policy issue because it does not offer the user a language choice or require opt-in before enforcing the locale.
No suspicious patterns detected.