ratings-snapshot
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (MEDIUM): The skill's setup instructions require installing the
octagon-mcppackage from the npm registry. The author 'OctagonAI' is not among the predefined trusted organizations, meaning the package content cannot be automatically verified for safety. - [REMOTE_CODE_EXECUTION] (MEDIUM): The configuration guides for Cursor and Claude Desktop use
npx -y octagon-mcp@latest. This command downloads and executes the package's binary immediately. Running unpinned versions (@latest) from unverified sources is a supply-chain risk as it allows for the execution of arbitrary code if the package is compromised. - [INDIRECT_PROMPT_INJECTION] (LOW): The skill passes a 'prompt' argument to the
octagon-agenttool. While the primary data points are financial tickers, the use of a natural language prompt field within the tool call creates a minor surface for injection if the underlying MCP server does not properly sanitize inputs or if it interprets instructions within the ticker string.
Audit Metadata