Rethinking Indirect Prompt Injection as a Test-Time Search Problem
Researchers frame indirect prompt injection as test-time search, showing added attacker compute improves vulnerability discovery and exploitation against tool-using agents.
The paper models indirect prompt injection as a test-time search over a task-dependent attack surface shaped by the environment, user task, and injection goal. The authors build an agentic attacker with a dedicated search harness that performs reconnaissance, structured strategy reasoning, and adaptive evaluation using victim-agent feedback. Experiments show more attacker test-time compute improves discovery and exploitation of injection vulnerabilities, with explicit strategy management needed to avoid redundant search. The results argue that agentic security evaluations should characterize attacker search procedures and compute budgets rather than treating attack success as budget-independent.
- Formalizes indirect prompt injection as adaptive test-time search over task-dependent attack surfaces.
- Agentic attacker uses reconnaissance, strategy reasoning, and victim feedback to refine attacks.
- More attacker compute increases both vulnerability discovery and successful exploitation.
- Ablations show strategy management prevents redundant search at larger compute budgets.
From the original article
1 min read at arxiv.orgWe formulate indirect prompt injection as a test-time search over a task-dependent attack surface induced by the environment, user task, and injection task. To operationalize this formulation, we introduce an agentic attacker with a dedicated search harness that performs environment reconnaissance, structured reasoning over attack strategies, and adaptive evaluation using victim-agent feedback.
By Duong M. Nguyen · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.