startup-equity-planner

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires connecting to an external Model Context Protocol (MCP) server at https://ai.planfi.app/mcp/free. This server hosts the logic and calculations for 83(b) and QSBS modeling, which is the primary function of the skill.
  • [COMMAND_EXECUTION]: The documentation provides setup commands for the user to execute (e.g., claude mcp add and npx skills add). These commands are standard for installing and configuring MCP-based skills and do not involve malicious escalation.
  • [DATA_EXFILTRATION]: Financial data provided by the user (such as share counts and strikes) is sent to the planfi.app infrastructure. This is the intended behavior of the skill as a 'thin orchestration layer' and is transparently disclosed in the README and SKILL.md files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 04:50 PM
Security Audit — agent-trust-hub — startup-equity-planner