liveBook · Manning

Untrusted input

As explained in AI Governance

Untrusted content is externally supplied information that has not been verified as safe or reliable.

A prompt injection can turn externally supplied content into instructions the model follows instead of its intended behavior. Inputs may come from public users, employee-pasted material, or documents ingested by retrieval-augmented generation (RAG) systems. section 4.2 section 4.5

Prompt injection targets the model’s behavior; a jailbreak specifically targets its safety guardrails. The consequences depend on what the application can do: manipulated output may be merely embarrassing, while access to sensitive data or real-world actions can make it a breach or operational failure. section 4.5 section 4.2

Assess the surrounding capabilities, not just the input:

  • Untrusted input, sensitive data access, and external communication together form the “Lethal Trifecta”; breaking any one element prevents the described data-leak attack. section 4.6
  • For permitted browser agents, use isolated profiles without saved credentials or corporate sessions; logged-out mode reduces capability while removing access to sensitive data. section 4.8.2
  • Use enterprise secure-browser solutions to log navigation and agent actions in real time, since traditional endpoint monitoring cannot see inside AI browsers. section 4.8.2
Figure 4.4 Image prompt injection causing a faulty decision in ChatGPT-5.

Illustrates image-embedded prompt injection causing a faulty decision. section 4.5

How AI Governance covers it

How deep it goes
Defines prompt injection and jailbreaks, then traces how data access and communication can escalate consequences.
Examples
Uses adversarial chatbot prompts, hidden instructions in RAG documents, image-based injection, and browser agents as examples.
What you can do after
Evaluate how untrusted input combines with data access and external communication to create data-leak paths.
How it connects
Connects prompt injection and jailbreaks with data access, external communication, and the Lethal Trifecta.

Also explained in

Compare how 2 books explain untrusted input →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of AI Governance. The section links point to the parts of the book it draws on.