historical-financial-ratings
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation provides a setup command for macOS that downloads and executes an installation script directly from Homebrew's official GitHub repository, which is a well-known and trusted service.
- [REMOTE_CODE_EXECUTION]: The skill instructs the user to run the
octagon-mcptool vianpx, which executes remote code from the npm registry. This is a standard mechanism for the vendor-provided MCP server functionality. Additionally, the Homebrew installation instruction involves piping a remote script to a shell. - [INDIRECT_PROMPT_INJECTION]: The skill ingests financial metrics and textual data from external websites and SEC filings via the
octagon-agenttool, creating a surface for indirect prompt injection. - Ingestion points: Data returned by the
octagon-agenttool as described inSKILL.mdandreferences/interpreting-results.md. - Boundary markers: None explicitly defined to isolate external data from the agent's instructions.
- Capability inventory: Accesses market intelligence, SEC filings, and financial website scraping via the Octagon MCP tools.
- Sanitization: No specific evidence of data sanitization or instruction-filtering before processing external content.
Audit Metadata