Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

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

Stavros Damianakis, Konstantinos Psounis

Published

Nov 18, 2026

Citations

0

Trust level

Moderate

Usefulness score

57/100 (Medium)

Extraction confidence

65% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 18, 2026

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

The abstract does not clearly name benchmarks or metrics.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
57/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

Abstract

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. A red teamer can achieve a high ASR by reusing a few techniques that work, leaving the others untested and absent from the attacks used to harden models. We present AutoPI, an adaptive red teamer designed to find many different ways to break a target, not just to break it often. AutoPI uses PIAtlas, a taxonomy of prompt-injection techniques, both to guide its search and to measure coverage. For each scenario, an attacker LLM writes an injection for every sub-technique in the taxonomy and then reworks the ones that fail using feedback from an LLM judge. The method is black-box and training-free, it plugs into existing benchmarks in place of their fixed attack templates, and it stays up to date as the taxonomy evolves. We evaluate AutoPI on AgentDojo and IPI Arena against open-weight and proprietary target models. Alongside ASR, we report technique coverage, the fraction of taxonomy classes, techniques, and sub-techniques that yield at least one successful injection. On AgentDojo, AutoPI finds a successful injection against Qwen3.6-35B in all six classes of the taxonomy and for more than 90% of its techniques. Against Claude Haiku 5.5, the most robust target we evaluate, it achieves between 20% and 50% higher ASR and between 25% and 400% higher class-level coverage than recent state-of-the-art adaptive red teamers, while requiring no training. We release our code and the generated attacks to support reproducible, coverage-aware evaluation.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Red Team

Directly usable for protocol triage.

"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."

Evaluation Modes

strong

Llm As Judge

Includes extracted eval setup.

"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."

Quality Controls

missing

Not reported

No explicit QC controls found.

"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."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"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."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"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."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
Yes
Feedback types
Red Team
Rater population
Not reported
Expertise required
Coding
Evaluation details
Evaluation modes
Llm As Judge
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

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.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • 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.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • 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).

Why it matters for eval

  • For each scenario, an attacker LLM writes an injection for every sub-technique in the taxonomy and then reworks the ones that fail using feedback from an LLM judge.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Red Team

  • Evaluation mode is explicit

    Detected: Llm As Judge

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    No metric terms extracted.