stock-performance

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the octagon-mcp server package using Node.js package managers (npx, bunx, pnpm). It also provides the official Homebrew installation script for macOS users (https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh) as a prerequisite.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for indirect prompt injection as it retrieves and processes stock data and financial intelligence from external sources, including web searches and SEC filings, through the octagon-agent tool.
  • Ingestion points: External market data and web search results are ingested into the agent context via the octagon-agent tool output (documented in SKILL.md).
  • Boundary markers: Not explicitly defined in the skill instructions; reliance is placed on the underlying agent platform's handling of tool outputs.
  • Capability inventory: The skill facilitates calls to the octagon-agent MCP tool but does not include local script execution or sensitive file system write operations.
  • Sanitization: No explicit sanitization or filtering logic is prescribed in the documentation for the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 09:12 PM
Security Audit — agent-trust-hub — stock-performance