linkfox-dld-product-billboard
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the execution of local Python scripts,
scripts/dld_product_billboard.pyandscripts/onboarding.py, to interact with the LinkFox API and facilitate user onboarding tasks such as login and payment. - [EXTERNAL_DOWNLOADS]: The skill initiates network communication with vendor-controlled domains, including
tool-gateway.linkfox.com,api.linkfox.com, andagent-api.linkfox.com, to fetch product ranking data and manage user account status. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-supplied search terms and display product information (such as titles and shop links) returned by the 1688 API.
- Ingestion points: Untrusted data enters the context through parameters like
keyWord,date,productIds, andgoodsUrlinSKILL.md. - Boundary markers: The skill does not implement explicit boundary markers or instructions to ignore potential injection patterns within the retrieved product data.
- Capability inventory: The associated scripts have the capability to perform network POST requests and write data files (JSON, logs, and QR code images) to the local file system.
- Sanitization: The skill performs keyword translation for non-Chinese inputs but does not specify further sanitization for data returned from the 1688 platform.
Audit Metadata