micro-influencer-growth-engine

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

• Third-party content exposure detected (high risk: 0.70). The workflow includes “Search for ‘Micro-Influencers’… in categories” and using platforms/agencies (e.g., 1stCollab/AKG Media) to source creators; at runtime this typically involves ingesting scraped/public web profiles or free-form messages/comments from those third parties into the agent’s LLM context, which is outsider-authored free text.