ecommerce-amazon-related-asins
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and processes external product data (such as titles and niche descriptions) from the Amazon marketplace via an external API. This data is untrusted and could potentially contain instructions aimed at influencing the agent's behavior when summarizing or displaying results.
- Ingestion points: API responses from the
/jiimore/pageAsinsByAsinendpoint, which are processed by thescripts/amazon_related_asins.pyscript. - Boundary markers: The skill does not implement specific delimiters or warnings for the agent to distinguish between data and potential instructions within product metadata.
- Capability inventory: The skill script performs network requests to the vendor's API and writes JSON output files to the local project directory under the
nexscope/folder. - Sanitization: The tool fetches and displays data directly from the API response without performing specific sanitization or filtering of the textual content.
Audit Metadata