amazon-competitor-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data from Amazon product listings through DataForSEO tools.
- Ingestion points: Product data is retrieved via
mcp__dataforseo__merchant_amazon_asin_live_advancedandmcp__dataforseo__merchant_amazon_products_live_advanced(SKILL.md, Workflow steps). - Boundary markers: The skill instructions do not define explicit delimiters or instructions to ignore potential commands embedded in the retrieved product titles or descriptions.
- Capability inventory: The skill is restricted to generating text reports in the chat; it does not possess file-writing, arbitrary network, or command execution capabilities.
- Sanitization: The skill does not implement validation or filtering of the external product data before analysis.
Audit Metadata