linkfox-seerfar-ozon-product-report-search
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill performs network requests to vendor-owned domains, including
tool-gateway.linkfox.com,api.linkfox.com, andagent-api.linkfox.com, to facilitate Ozon product data retrieval and account onboarding. These communications are part of the skill's core functionality. - [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted data from Ozon marketplace listings.
- Ingestion points: Product information is fetched via the Seerfar API in
scripts/seerfar_ozon_product_report_search.py. - Boundary markers: No explicit delimiters are implemented in the data processing scripts.
- Capability inventory: The skill can write JSON data to the local filesystem under the
linkfox/directory and print results to the terminal. - Sanitization: Standard Python JSON parsing is utilized to handle API responses.
- [PERSISTENCE_MECHANISMS]: Documentation in
references/onboarding.mdprovides instructions for users to persist API keys by manually modifying shell profile files (.zshrc,.bashrc) or Windows environment variables. This is a standard practice for managing development credentials. - [DYNAMIC_EXECUTION]: The script
scripts/seerfar_ozon_product_report_search.pyattempts to modifysys.pathto include a_shareddirectory for local utility imports. This is a common pattern for modular skill development and does not involve loading code from untrusted external sources.
Audit Metadata