skills/nexscope-ai/nexscope-ecommerce-skills/ecommerce-amazon-product-research-api/Gen Agent Trust Hub
ecommerce-amazon-product-research-api
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence agent behavior.\n
- Ingestion points: External data, including product reviews and market descriptions, enters the agent context via API responses processed in
scripts/amazon_reviews.py,scripts/jiimore_get_niche_review.py, and other research scripts.\n - Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are present to isolate external data from system prompts.\n
- Capability inventory: The skill can perform network operations via
urllib.requestandrequests, and write to the local file system usingopen()in scripts likescripts/aba_query.py.\n - Sanitization: No specific filtering or sanitization of natural language instructions within the ingested data was observed.
Audit Metadata