longbridge-post-investment

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly instructs the agent to fetch and read third‑party public content (e.g., "Fetch recent news" and the longbridge news <SYMBOL> / longbridge financial-report CLI calls) and to use that content to generate recommendations, so untrusted public news/website content could influence agent actions.