amazon-niche-finder
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves data from external sources, specifically Amazon product pages and user reviews, using the
web_fetchtool. This introduces a surface for indirect prompt injection where adversarial content hosted on these external pages could attempt to override the agent's instructions. - Ingestion points: The skill utilizes
web_fetchto collect BSR (Best Sellers Rank), reviews, ratings, and monthly review growth from Amazon product pages. - Boundary markers: There are no explicit instructions or delimiters defined to isolate the fetched external data from the agent's primary reasoning instructions.
- Capability inventory: The skill leverages
web_searchandweb_fetchto perform its analysis. - Sanitization: The instructions do not specify any validation, filtering, or escaping mechanisms for the data retrieved from external websites.
Audit Metadata