amazon-sales-estimator
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its data ingestion features.
- Ingestion points: SKILL.md (Mode B and Mode C) instructs the agent to fetch product data using web_fetch and web_search.
- Boundary markers: There are no boundary markers or instructions to treat external data as untrusted content.
- Capability inventory: The skill utilizes web_fetch and web_search, with no access to sensitive files or command-line execution.
- Sanitization: No explicit sanitization or validation of the fetched product information is performed.
- [EXTERNAL_DOWNLOADS]: The skill references standard vendor resources for installation and documentation.
- It provides an npx command to add additional skills from the nexscope-ai repository.
- It includes links to the vendor's official website at nexscope.ai and associated GitHub projects.
Audit Metadata