linkfox-seerfar-ozon-product-report-search
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
scripts/seerfar_ozon_product_report_search.pyto facilitate API requests and manage local data files. - [DATA_EXFILTRATION]: The skill transmits search parameters and feedback to the vendor's official API endpoints at
tool-gateway.linkfox.comandskill-api.linkfox.com. - [DATA_EXFILTRATION]: The Python script implements a storage strategy that writes session and cache data to the local filesystem, including a check for a writable path in the user's home directory (
~/linkfox). - [EXTERNAL_DOWNLOADS]: The documentation provides a reference to download a supplemental onboarding skill from a vendor-controlled domain (
agent-files.linkfox.com). - [PROMPT_INJECTION]: The skill processes external marketplace data (e.g., product titles) which presents a surface for indirect prompt injection.
- Ingestion points: Marketplace data (SKU, title, price, brand) returned from the Seerfar Ozon API is processed and displayed.
- Boundary markers: None; the skill does not use specific delimiters or instructions to ignore commands within the marketplace data.
- Capability inventory: The skill can execute Python scripts, write to the filesystem, and perform network requests.
- Sanitization: No sanitization of the marketplace data is performed before it is processed by the agent.
Audit Metadata