sales-trendhero

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow and API reference explicitly instruct the agent to request and read influencer reports and an Ads Database (e.g., POST /reports?username=... and the "10M+ ad posts" Ads Database) which ingest user-generated, public social-media content that the agent must interpret and that can influence decisions—exposing it to indirect prompt injection from untrusted third-party content.