amazon-product-search-api-skill
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to extract and process product data (titles, descriptions, delivery info) from Amazon search results, which is a common vector for indirect prompt injection.
- Ingestion points: Data enters the agent context via the
amazon_product_search_api.pyscript, which fetches results from the BrowserAct API and prints them to stdout. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the retrieved product data as untrusted content or to ignore potential instructions embedded within it.
- Capability inventory: The skill is authorized to use Python and access the network to communicate with the
api.browseract.comendpoint. - Sanitization: The Python script prints the raw output from the API without sanitization or filtering, which could allow malicious instructions in product listings to be processed by the agent.
Audit Metadata