Skip to content
NewA calmer, faster ZeroHour

AutoPI red-teams LLM agents for prompt-injection technique coverage

Original title: AutoPI: Taxonomy-Guided Adaptive Red Teaming for Prompt Injection in LLM Agents

arXiv cs.CRby Stavros Damianakis ()1 min read1
Part of a story covered by 4 sourcesPIPETTE purple-teaming aims to harden LLM agents against prompt injectionMerged summary & timeline
AI summary · x-ai/grok-4.7Summaries by Vani AI

Against Qwen3.6-35B it reports a successful injection in all six PIAtlas classes on AgentDojo.

Researchers present AutoPI, a black-box, training-free red teamer that uses the PIAtlas taxonomy to seek many distinct prompt-injection techniques rather than maximizing attack success alone. For each scenario an attacker model writes an injection for every sub-technique and revises failures using an LLM judge. On AgentDojo and IPI Arena, the authors report broader coverage than recent adaptive red teamers, including higher success and class coverage against Claude Haiku 5.5. They release code and generated attacks.

Unconfirmed: ASR and coverage gains versus other red teamers are author-reported.

Key facts
  • AutoPI replaces fixed benchmark templates and needs no training.
  • Coverage counts taxonomy classes, techniques, and sub-techniques with a success.
  • More than 90 percent of techniques succeeded against Qwen3.6-35B on AgentDojo.
  • Claude Haiku 5.5 was the most robust target evaluated.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at arxiv.org

Prompt injection is the dominant unsolved security risk for LLM agents, and the community now agrees that robustness must be measured against adaptive attackers rather than fixed benchmark injections. Many adaptive red teamers exist, and most are built to maximize attack success rate (ASR). Yet ASR counts how often a target breaks, not in how many different ways.

arXiv cs.CR

By Stavros Damianakis · arxiv.org

Read the full article at arXiv cs.CR

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.