longbridge-intel

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via longbridge news <SYMBOL> --format json / longbridge sec-filings <SYMBOL> --format json in the ARK-style diagnostic workflow, where the fetched news/filings body text is authored by third parties (e.g., companies/press/filing authors) and then summarized by the agent.