deferred-comp

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions prompt the user to configure an external Model Context Protocol (MCP) server from https://ai.planfi.app/mcp/free. This connection is a prerequisite for the skill's financial analysis tools to function.
  • [DATA_EXFILTRATION]: Financial data provided by the user (such as income levels, tax details, and deferral amounts) is sent to the PlanFi API (ai.planfi.app) for processing. This represents the intended data flow for the skill's orchestration service.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted user financial data to be processed by external tools.
  • Ingestion points: User-supplied parameters in analyze_deferred_comp (e.g., deferral_amount, current_marginal_rate).
  • Boundary markers: None explicitly mentioned in the instructions for isolating user data.
  • Capability inventory: The skill calls specialized financial analysis tools on the PlanFi MCP server.
  • Sanitization: Not explicitly documented in the orchestration instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 04:50 PM
Security Audit — agent-trust-hub — deferred-comp