NUWA RESEARCH RECORD
AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
Original publication ↗ · BibTeX · RISThe tested approach finds stronger attacks than evaluated baselines and shows some cross-task and cross-model transfer.
Research question
How can adaptive black-box testing reveal indirect prompt-injection weaknesses?
Design & assumptions
AgentVigil evaluates automated adaptive red-teaming against personal-assistant and web-agent benchmarks, including transfer and defense studies.
Findings
The tested approach finds stronger attacks than evaluated baselines and shows some cross-task and cross-model transfer.
Limits & counterevidence
Results depend on query budget, accessible injection surface and target versions. Automated attack discovery is a testing method rather than a comprehensive security guarantee. No reusable attack payloads are included.
Source evidence
No structured numerical extraction is available in this reading package.
Reading scope & review
Selected original HTML sections and table context; not a complete paper/appendix audit or independent reproduction.
Model-assisted reading; independent evidence review pending.
Check the original source ↗