Skip to content
AI Security

Interview question · Software, Data & Model Supply Chain

How can untrusted issue and pull request text turn an AI agent in CI into a supply-chain attack, and how do you run one safely?

CI already mixed untrusted input with powerful tokens. Adding an agent that reads issue text and can act turns a shell-injection problem into a prompt-injection problem. The scored answer fixes both.

hardNewPreparation tags: Google, Anthropic, OpenAIUpdated Nov 2026

CI already mixed untrusted input with powerful tokens. Adding an agent that reads issue text and can act turns a shell-injection problem into a prompt-injection problem. The scored answer fixes both.

Make your first attempt

What would you say before reading the answer?

  1. 01 State the assumptions your answer depends on.
  2. 02 Explain the mechanism and choose a control.
  3. 03 Name a condition that would change your decision.

The worked answer includes an approach, scoring criteria and follow-up questions. Compare the reasoning with your own.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 529 remaining answers · $25

Every worked answer in all 17 topics, every lesson in every course, the full concept curriculum, the complete practice-test bank, and the downloadable security field guides.

6 months · One payment · No auto-renewal

What if · the follow-ups in this answer

The answer works through 4 follow-ups like an interviewer would

An open-source project adds an AI action that runs on every new issue, with a repository-scoped personal access token so it can label issues, comment and open fix pull requests. A week later a release contains code nobody on the team wrote.

  1. What is the most likely path?
  2. What do you do immediately?
  3. How should the action be rebuilt?
  4. How do you summarise AI agents in CI?

Each rung has a nudge, a model answer, the principle that carries over and the weak answer to avoid. Premium opens every answer and ladder.

UP NEXT ON YOUR JOURNEY
Next in this trackAll release checks are green, but they assessed different revisions. Can the release proceed?Popular right nowWhat security risks does the Model Context Protocol (MCP) introduce?Popular right nowExplain the lethal trifecta and use it to triage an agent design in two minutes.
DISCUSSION · 0

No comments yet. Share a correction or a different way to answer it.