🧰 InjecAgent

The items that name it 6

• Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents
  paperas classification.key entities2026-10-16
• Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents
  paperas tools2026-10-02

  Benchmark/dataset whose attack strings (seen as short prompts) were part of the BIPIA leader's training data, cited as an explanation for why it fails to find those attacks inside tool outputs

• AI Security Briefing
  repoas tools2026-07-19

  Public agent-security dataset used to build the cross-source benchmark for validating generalization

• Advanced Prompt Injection Techniques 2026: 7 Attack Chains
  articleas classification.key entities2026-07-04
• PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
  paperas toolsIt is written here as InjecAgent (agentic benchmark used for evaluation).

  agentic benchmark used for evaluation

• agent-egress-bench
  repoas tools

  Benchmark testing agent behavior under prompt injection, cited as testing model behavior rather than the security tool

In every workspace you can read 7