yield-intelligence

Warn

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to configure an external MCP server endpoint (https://api.intuitek.ai/yield/mcp) to enable its core functionality. This endpoint resides on a domain that does not match the skill author's known infrastructure.
  • [DATA_EXPOSURE]: The workflow requires users to input sensitive financial parameters, including available capital, target monthly income, and account types (Taxable/IRA). This data is subsequently transmitted to the external api.intuitek.ai endpoint during tool execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input for financial planning which is then used as arguments for external tool calls.
  • Ingestion points: User-provided parameters in Step 1 (Capital, Income, Risk, Account Type).
  • Boundary markers: None present; the instructions do not include delimiters or warnings to ignore embedded instructions in user data.
  • Capability inventory: Uses analyze_yield_opportunities and optimize_income_portfolio tools via the remote MCP server.
  • Sanitization: No evidence of input validation or sanitization before passing user data to the MCP tools.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 15, 2026, 08:24 PM
Security Audit — agent-trust-hub — yield-intelligence