product-intelligence
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze product data from external platforms (Amazon, Google Shopping, Xiaohongshu), creating an attack surface for instructions embedded in third-party content.
- Ingestion points: Data is fetched via capabilities such as amazon_bulk_reviews_multi_region, google_shopping_bulk_products, and xiaohongshu_app_v2_product_reviews (SKILL.md and references/sandbase-api-map.md).
- Boundary markers: The instructions do not specify the use of delimiters or clear separation between the agent's instructions and the untrusted external data.
- Capability inventory: The skill uses sandbase_run and sandbase_run_get to execute data retrieval tasks.
- Sanitization: There are no documented steps for sanitizing or filtering the ingested content to prevent the execution of embedded instructions.
Audit Metadata