linkfox-tiktok-shop-product-detail
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes Python scripts (
tiktok_shop_product_detail.pyandonboarding.py) to perform API calls and manage user accounts. These scripts are executed with specific JSON parameters to interact with LinkFox services. - [EXTERNAL_DOWNLOADS]: The skill connects to LinkFox's official infrastructure (
tool-gateway.linkfox.com,api.linkfox.com, andagent-api.linkfox.com) to retrieve product data and handle authentication/billing flows. These operations are consistent with the vendor's provided services. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from TikTok Shop product listings. While this data is handled as structured JSON, it represents an ingestion surface for third-party content.
- Ingestion points: Product data is fetched via the LinkFox gateway API in
scripts/tiktok_shop_product_detail.py. - Boundary markers: The instructions guide the agent to extract specific fields from JSON files or summaries, reducing the risk of accidental instruction obedience.
- Capability inventory: The skill can execute Python scripts, perform network requests to vendor domains, and write data files to the local
linkfox/directory. - Sanitization: Content is parsed as structured JSON before being presented or summarized by the agent.
- [SAFE]: The skill follows secure practices by saving sensitive API responses to a local session-specific directory for user review rather than passing large raw data blobs directly into the LLM context. Authentication and payment instructions are provided for manual user execution, maintaining human-in-the-loop control.
Audit Metadata