Quiz collegato alla guida · Difficile Livello

Data Exfiltration via Markdown Images Quiz

Tests the model-renderer-network attack chain, remote image requests, output sanitization, browser controls, and safe testing practices.

Percorsi guida correlatiMarkdown Image Data Exfiltration
Domanda 1 di 8

Quale sequenza crea il rischio di esfiltrazione tramite immagini Markdown?

Anteprima di ogni domanda8 domande

Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.

  1. Quale sequenza crea il rischio di esfiltrazione tramite immagini Markdown?
    • Injection influences output, a renderer loads a remote image URL, and data may be sent externally
    • A model writes plain text and no client renders it
    • A browser disables network access
    • An image is stored locally with no remote request
  2. Cosa può contenere l'URL dell'immagine remota in questo schema di attacco?
    • A local file permission
    • Sensitive conversation data in its path or query
    • Only an image’s pixel values
    • The model’s weights
  3. Perché questo è sia un problema di gestione dell'output sia un problema di iniezione di prompt?
    • The model never sees private context
    • Only the database controls network traffic
    • The downstream renderer may turn untrusted generated Markdown into a network request
    • Markdown cannot contain links
  4. Quale controllo dell'output può impedire che i tag immagine remoti attivino richieste?
    • Add a prompt asking for longer answers
    • Display raw HTML
    • Allow every image host
    • Escape or strip untrusted Markdown image tags before rendering
  5. Cosa controlla una politica restrittiva delle fonti delle immagini?
    • Which hosts a browser may load images from
    • Which facts the model remembers
    • Whether the prompt contains a user request
    • How many tokens a model uses
  6. How can a team safely test this behavior?
    • Disable all logging and controls
    • Use synthetic markers and a controlled endpoint in a sandbox
    • Use real secrets in a public prompt
    • Test only by reading the answer text
  7. Why is “do not reveal secrets” in a prompt not enough?
    • The image host is part of the model
    • A browser cannot make HTTP requests
    • Prompt instructions do not sanitize rendered output or enforce network policy
    • Markdown ignores all prompts
  8. Which conditions determine whether a particular application is exposed?
    • Only the model provider’s name
    • Only whether the user uses dark mode
    • The title of the conversation
    • Model context/output, Markdown renderer behavior, and allowed network requests