Skip to content
NewA calmer, faster ZeroHour

Larger prompt-injection red-team piles can weaken agent defenses

Original title: Your AI red team may be finding the same prompt injection thousands of times

Help Net Securityby Mirko Zorz ()4 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

A Qwen3-4B retrained on PISmith’s larger haul was hijacked on 47.5% of unseen stress-test tasks, versus 27.5% for RL-Hammer.

Researchers at the University of Waterloo, Zhejiang University and KTH found that retraining an agent on more successful prompt injections made it easier to hijack in three of four tests. PISmith beat RL-Hammer on raw attack volume against Qwen3-4B, but the resulting defense was weaker. Their PIPETTE system rewards new techniques and checks that each action serves the user’s request. On AgentDojo, stock injections succeeded on less than half a percent of attempts against PIPETTE-trained agents.

Unconfirmed: The authors have not checked their technique grader against human judgment and do not claim narrow coverage is the sole cause.

Key facts
  • PISmith broke 68.75% of 560 tasks and returned 7,132 working attacks.
  • RL-Hammer broke 33.39% of tasks and returned 4,282 attacks.
  • On 40 known weak tasks, the PISmith-trained model was hijacked 19 times versus 11.
  • Attackers rewriting injections for about 250 tries reached up to 10% of those tasks.
  • Hardened Qwen3-4B finished 64.95% of clean tasks, versus 61.86% originally.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

4 min read at helpnetsecurity.com

AI agents retrained on a bigger pile of prompt injection attacks came out easier to hijack in three of four tests run by researchers at the University of Waterloo, Zhejiang University and KTH Royal Institute of Technology. The automated red-teaming tool that found more working attacks produced the weaker defense.

Help Net Security

By Mirko Zorz · helpnetsecurity.com

Read the full article at Help Net Security

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.