amazon-private-label
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external environments, creating an attack surface for indirect prompt injection.\n
- Ingestion points: The workflow relies on gathering product and market information from user messages and market trends via the
web_searchtool (SKILL.md, README_CN.md).\n - Boundary markers: The skill instructions do not specify any delimiters or safety markers to differentiate between the agent's core instructions and the external data being analyzed.\n
- Capability inventory: The agent is authorized to use the
web_searchtool for automated information retrieval.\n - Sanitization: There are no requirements or logic provided for the sanitization of content retrieved from the web before it is integrated into the agent's analysis context.
Audit Metadata