longbridge

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions include steps to download and install additional components from the official Longbridge repository on GitHub (github.com/longbridge/skills).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as stock market quotes, financial news, and analyst ratings, which could theoretically contain instructions intended to influence the agent's behavior.
  • Ingestion points: Data enters via the longbridge CLI tool which fetches market data, company fundamentals, and news from external APIs.
  • Boundary markers: None mentioned in the provided instructions.
  • Capability inventory: Uses subprocess calls to the longbridge binary and can potentially use MCP tools at runtime.
  • Sanitization: No explicit sanitization or filtering of external financial content is described in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:49 PM
Security Audit — agent-trust-hub — longbridge