linkedin-ads-optimization

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

• Third-party content exposure detected (high risk: 0.70). The required workflow explicitly instructs using ColdIQ MCP/API “competitive research” (including Ads Library-style creative/audience data) at runtime, which will be free-text retrieved from an external service other than the operating user, creating an indirect prompt-injection exposure path into the agent’s LLM context.