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.
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.
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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