aihot

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow explicitly instructs the agent to curl the public API at https://aihot.virxact.com (e.g., /api/public/items and /api/public/daily) to ingest news items and sourceUrls from arbitrary public websites, so it directly consumes untrusted third-party web content that can influence the agent's outputs and subsequent actions.