OAuth discovery metadata points your agent at an internal URL. How would you prevent SSRF?

Instruction: Explain which fetches are at risk, how to enforce destination policy, and how to test redirects and DNS changes.

Context: Secure unfamiliar OAuth metadata URLs fetched by MCP clients and authorization servers without breaking reviewed enterprise integrations.

Updated

Prepare a stronger answer

I’d treat every discovered URL as untrusted input to a privileged network client. That includes resource metadata, authorization-server metadata, and any endpoints taken from those documents. A URL using HTTPS can still target an internal service, so I’d enforce both an allowed scheme and a destination policy...

This member answer includes:

  • • A complete, copyable sample answer
  • • A practical walkthrough
  • • Common mistakes and how to avoid them
  • • Guidance for adapting the answer to your experience
  • • Answered interviewer follow-ups
Unlock the full answer and preparation guide

One payment for one year of full access. No automatic renewal.

See pricing and everything included

Your preparation path

Work through these questions in order. Read the answer aloud, then explain it in your own words.

1. Start with the foundations

Build the vocabulary and explain the core decisions.

  1. Why is prompt injection different from ordinary bad input? Free sample
  2. How do you separate policy enforcement from model style instructions? Free sample
  3. What information should never flow from untrusted content straight into tool execution? Free sample

2. Apply it to a real workflow

Practice diagnosis, validation, and everyday tradeoffs.

  1. How do you decide where to place guardrails in a multi-step agent workflow? Free sample
  2. A summarization workflow passes unsafe content from retrieval into a downstream action. How would you fix it? Member answer
  3. A reviewer approves a high-risk action because the model framed it confidently. How would you reduce that risk? Member answer

3. Prepare for senior discussions

Explain failure boundaries, recovery, and production choices.

  1. A multi-agent system routes around one guardrail because another agent has broader permissions. How would you fix it? Member answer
  2. OAuth discovery metadata points your agent at an internal URL. How would you prevent SSRF? Member answer
  3. Why can a localhost MCP server still be exposed to attacks from a website? Member answer

Related Questions