linkfox-mercado-product-selection

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Python scripts (scripts/linkfox_mercado_product_selection.py and scripts/onboarding.py) to interact with the LinkFox gateway. These scripts are invoked via standard command-line patterns in a development environment.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to tool-gateway.linkfox.com, api.linkfox.com, and agent-api.linkfox.com. These are all official domains belonging to the vendor (linkfox-ai) for tool execution and user onboarding.
  • [CREDENTIALS_UNSAFE]: The skill uses environment variables LINKFOX_AGENT_API_KEY and LINKFOXAGENT_API_KEY for authentication. This is a standard security practice and the instructions explicitly warn against sharing these keys in user-facing output.
  • [DATA_EXFILTRATION]: While the skill reads and processes Mercado Libre data, it follows a strict local persistence policy. Results are saved to a versioned linkfox/ directory within the project workspace for the user's review, preventing silent exfiltration to unauthorized endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 12:41 AM
Security Audit — agent-trust-hub — linkfox-mercado-product-selection