ecommerce-ozon-category-search
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
scripts/ozon_category_search.pyto perform API requests and handle data persistence. - [EXTERNAL_DOWNLOADS]: Fetches e-commerce analytics data from the vendor's API endpoint via a proxy configured in the environment. These downloads are core to the skill's function of retrieving Ozon marketplace data.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted product titles, brand names, and seller information from the Ozon marketplace.
- Ingestion points: External data is ingested through the
call_apifunction inscripts/ozon_category_search.py. - Boundary markers: The skill instructions recommend presenting data in a clear table format but do not specify explicit delimiters for the external content.
- Capability inventory: The associated script has capabilities for network communication and file system writes to the local project directory.
- Sanitization: The script does not perform sanitization on the retrieved marketplace data before presenting it to the agent.
Audit Metadata