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.py to 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_api function in scripts/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
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:13 AM
Security Audit — agent-trust-hub — ecommerce-ozon-category-search