iFinD-Finance-Data

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The Python script call.py defines a dependency on the requests library for handling HTTP communications.
  • [COMMAND_EXECUTION]: Both the Python (call.py) and Node.js (call-node.js) scripts perform network operations to the vendor's API at api-mcp.51ifind.com. These scripts include code that explicitly disables SSL/TLS certificate verification (verify=False in Python and rejectUnauthorized: false in Node.js), creating a vulnerability to man-in-the-middle (MITM) attacks.
  • [PROMPT_INJECTION]: The skill ingests and processes external data (financial indicators, news, and announcements), which serves as an attack surface for indirect prompt injection.
  • Ingestion points: API response data retrieved from iFinD servers and processed within call.py and call-node.js.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the scripts or instructions.
  • Capability inventory: The skill possesses network communication capabilities via the provided scripts to interact with the iFinD MCP servers.
  • Sanitization: The skill does not implement validation or sanitization of the data retrieved from external API endpoints before passing it to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 05:15 AM
Security Audit — agent-trust-hub — iFinD-Finance-Data