stock-sdk-mcp
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external financial markets, creating a surface for indirect prompt injection where malicious instructions could be embedded in stock names or market summaries.
- Ingestion points: Data enters the context via
get-quotes-by-query,get-industry-list, and other market data tools inmarket-overview.md,realtime-monitor.md,stock-analyst.md, andstock-screener.md. - Boundary markers: The instructions lack delimiters or warnings to the agent to disregard instructions contained within the fetched market data.
- Capability inventory: The skill uses
uvxandnpxto execute shell commands, which could be abused if the agent is successfully injected. - Sanitization: There is no evidence of filtering or escaping external data before it is presented to the agent.
- [EXTERNAL_DOWNLOADS]: The skill fetches the
stock-sdk-mcppackage from the official NPM registry at runtime using thenpxcommand. - [COMMAND_EXECUTION]: Core functionality relies on executing shell commands via
uvx mcp2clito interact with the stock data provider.
Audit Metadata