linkedin-engagement

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

• Third-party content exposure detected (high risk: 0.70). SKILL.md requires using the ColdIQ MCP/API to “surface” influencers and extract post engagement, which at runtime will bring in third-party-authored text like LinkedIn post/comment content or user profiles from ColdIQ/public sources into the agent’s LLM context (outsider-origin free text via ColdIQ integration).