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-mcp package 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-agent tool. 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
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 05:04 AM