longbridge-value-screen

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute the longbridge CLI tool with various subcommands (constituent, calc-index, valuation, dividend) to retrieve financial metrics and index data.
  • [EXTERNAL_DOWNLOADS]: The skill recommends integration with an external MCP server located at https://openapi.longbridge.com/mcp to fetch stock data when the local CLI is unavailable. This endpoint belongs to the official domain of the Longbridge financial service.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes untrusted data from external financial markets.
  • Ingestion points: Stock index constituent lists and financial KPIs fetched via longbridge CLI or MCP tools (SKILL.md).
  • Boundary markers: None identified; external data is interpolated directly into the analysis workflow.
  • Capability inventory: The skill executes local shell commands via the longbridge CLI (SKILL.md).
  • Sanitization: No specific escaping or validation logic is defined for the external stock names or metadata processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 01:25 PM
Security Audit — agent-trust-hub — longbridge-value-screen