post-to-campaign

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

• Third-party content exposure detected (high risk: 0.85). The required workflow reads an outsider-authored LinkedIn post at runtime (via the LGM MCP get_linkedin_post using a user-supplied URL) and then uses that post text as the angle for generated campaign copy, so the LLM context is fed outsider free text.