linkfox-echotik-list-seller-product
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted product information from the external EchoTik API, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: Data is retrieved in
scripts/echotik_list_seller_product.pyfrom the/echotik/listSellerProductendpoint. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are included in the processing of API responses.
- Capability inventory: The skill possesses network access to vendor-controlled domains and local file system write access.
- Sanitization: No explicit sanitization or filtering is performed on the data received from the API.
- [COMMAND_EXECUTION]: The skill is designed to run local Python scripts (
scripts/echotik_list_seller_product.pyandscripts/onboarding.py) as its primary operational method. The instructions guide the agent to execute these scripts using various parameters, including user-supplied data. - [EXTERNAL_DOWNLOADS]: The
onboarding.pyscript mentions standard Python dependencies (requests,qrcode,pillow) and provides instructions for manual installation from official registries if they are missing.
Audit Metadata