income-statement
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's setup documentation provides instructions to install the Octagon MCP server via
npxand references the official Homebrew installation script. These resources originate from the skill's vendor or well-known, trusted services. - [COMMAND_EXECUTION]: The installation and configuration process involves executing shell commands to manage environment variables and initialize the MCP server using tools like
npx,npm, andnode. - [INDIRECT_PROMPT_INJECTION]: The skill ingests financial data from an external API, which creates a potential surface for indirect prompt injection as the instructions do not implement specific boundary markers or data validation for the tool output.
- Ingestion points: Data retrieved from the
octagon-agenttool as described inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or provide the agent with guidance to ignore instructions potentially embedded in the tool's output.
- Capability inventory: The skill utilizes the
octagon-mcpserver tools for data retrieval, which are then used by the agent to perform financial analysis. - Sanitization: There is no mention of sanitizing or validating the contents of the API response before it is processed by the agent.
Audit Metadata