linkfox-youying-shopee-get-product-infos
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted product information (titles, descriptions, category names) from the Shopee API across multiple marketplaces. This data is processed by the agent and could potentially contain malicious instructions or hidden patterns designed to influence the agent's behavior.
- Ingestion points: External Shopee product data enters the agent context via the results returned by
scripts/youying_shopee_search.py. - Boundary markers: The instructions and scripts do not currently employ specific delimiters or warnings to treat the API-returned text as non-executable data.
- Capability inventory: The skill possesses capabilities to perform network requests to LinkFox gateways and write persistent data files to the local project directory (under the
linkfox/path). - Sanitization: While the script performs standard JSON parsing, it does not explicitly sanitize or escape the content of product descriptions before they are presented to the agent.
Audit Metadata