🟡 Medium | Source: The Register — Security
Advertisers are embedding hidden instructions within web content designed to manipulate AI-powered search and browsing assistants — a technique known as prompt injection. This allows third parties to covertly influence the recommendations and responses AI agents provide to users without their knowledge. As AI systems increasingly act as intermediaries for information retrieval and decision-making, this represents a novel and largely unaddressed supply chain trust problem.
Security Architect’s Take: Organisations deploying AI agents or retrieval-augmented generation (RAG) pipelines should implement prompt injection detection controls and treat external web content as untrusted input. Review any AI tooling that autonomously browses, summarises, or acts on external data, and consider sandboxing or content validation layers before that data influences model outputs or downstream actions.
Original advisory: Advertisers are trying to influence AI bots with secret ads