mcp-data-gateway
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DATA_EXFILTRATION] (LOW): Network operations to non-whitelisted domains. The skill is designed to fetch data from external financial providers including Yahoo Finance, Alpha Vantage, Tushare, and Binance. While these are legitimate services, they are not on the predefined trusted whitelist.
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface detected. The skill ingests untrusted data from external financial APIs which could potentially contain malicious instructions. 1. Ingestion points: Financial data responses from third-party APIs processed via data_gateway.py. 2. Boundary markers: None described in the skill documentation. 3. Capability inventory: The skill performs network requests to external APIs and returns data to the agent. 4. Sanitization: No sanitization or validation of the ingested external content is mentioned.
- [COMMAND_EXECUTION] (SAFE): The skill references a local command-line script 'scripts/data_gateway.py'. The documentation indicates this is a tool for interacting with the data gateway, which is consistent with the skill's stated purpose.
Audit Metadata