str-investment-analyzer

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to connect to an external Model Context Protocol (MCP) server at https://ai.planfi.app/mcp/free. This remote service provides the core computational logic and market datasets required for the skill to function. \n- [DATA_EXFILTRATION]: User-supplied financial information, such as property purchase prices, locations, and personal income details, is transmitted to the planfi.app backend. This data flow is central to the skill's primary purpose and is explicitly disclosed in the documentation. The target domain is managed by the skill's authoring organization. \n- [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection through its ingestion of external tool data. \n
  • Ingestion points: Data is ingested from the outputs of the forecast_str_market and related tools provided by the Planfi MCP (SKILL.md). \n
  • Boundary markers: The instructions in SKILL.md provide specific guidance on which data fields to present to the user, which helps structure the raw tool output. \n
  • Capability inventory: The skill's capabilities are limited to calling the specified MCP tools; it lacks local file system access or the ability to execute arbitrary subprocesses. \n
  • Sanitization: There are no explicit instructions for the agent to sanitize or escape text content returned by the external tools before presenting it to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 04:50 PM
Security Audit — agent-trust-hub — str-investment-analyzer