longbridge-competitive-analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly fetches and ingests third‑party content — e.g., "Fetch comparative financials and valuation" and "Fetch recent news" (via the CLI command longbridge news <SYMBOL>) — meaning untrusted public news/financial sources are read and can materially influence the agent's analysis and actions.