ev-lending-risk-monitor

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows its stated purpose of providing EV market intelligence without any detectable malicious patterns.
  • [COMMAND_EXECUTION]: The skill uses Marketcheck's own MCP tools (mcp__marketcheck__get_sold_summary and mcp__marketcheck__search_active_cars) to retrieve market data. These operations are scoped to the vendor's functionality and do not involve arbitrary shell command execution.
  • [DATA_EXPOSURE_&_EXFILTRATION]: The skill references a project memory file (marketcheck-profile.md) to extract user preferences such as target states and country. This is a standard practice for personalizing agent responses and does not constitute unauthorized data exposure.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes external data from market APIs, it employs strict data extraction logic, pulling only specific numeric and categorical fields (e.g., sold_count, average_sale_price, make, model). This targeted extraction significantly mitigates the risk of indirect prompt injection from the processed data source.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 02:40 AM
Security Audit — agent-trust-hub — ev-lending-risk-monitor