Concept · 25 episode(s)

Prompt Injection

← all concepts

Definition

Prompt injection is an attack where adversarial instructions are smuggled into data that a model later reads — a web page, an email, a tool output — causing the model to ignore its real instructions and follow the injected ones. It’s the defining security problem of LLM agents.

Episodes covering this

  1. 246
    160 Perfect Refusals, And The Refusals Were The Leak
    Inadvertent Context Leakage in Language Models
    Fairoze, Mangaokar, Chaudhuri et al. · University of California·20 min·Aug 21, 2026
  2. 243
    How a Hundred Meaningless Word Choices Add Up to Flip a Model's Answer
    Model Hypnosis: Strong control of AI via additive subliminal effects
    Boix-Adsera, Tessler · University of Pennsylvania·18 min·Aug 18, 2026
  3. 238
    How a Cheap Model Reads the Flagship's Secret Reasoning Aloud
    Stealing Reasoning Traces from Proprietary LLM APIs
    Panfilov, Schmotz, Shumailov et al. · MATS Research·19 min·Aug 11, 2026
  4. 236
    Why a Printed 'OPERATOR OVERRIDE' Note Redirects Robot Planners
    Hijacking Robots with a Piece of Paper: A Systematic Study of Physical Prompt Injection in VLM-Controlled Robots
    Samarakoon, Muthugala, Sachinthana et al. · Singapore University of Technology and Design·21 min·Aug 07, 2026
  5. 227
    Poisoned Bug Reports Fooled Coding Agents Two Times Out of Three
    IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests
    Singh, Yang, Chen · Concordia University·18 min·Jul 24, 2026
  6. 226
    How a Speed Feature Lets a Stranger Poison Your AI's Answer
    HijackKV: New Threat in Position-Independent KV Cache Reuse
    Zhang, Wang, Zhang et al. · The Pennsylvania State University·16 min·Jul 23, 2026
  7. 208
    The Blank Space in Your AI Approval Box That Isn't Empty
    Unicode TAG-Block Concealment of Tool-Metadata Payloads in the Model Context Protocol: An Approval-View Fidelity Gap Across Three Independent Server Implementations
    Rashidi · Department of Computer Science·15 min·Jul 08, 2026
  8. 202
    How Do You Know an AI Agent Actually Refused? Check the World, Not the Words
    Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
    Feng, Lin, Wen et al. · AntGroup / Hunan Institute of Advanced Technology·18 min·Jul 06, 2026
  9. 184
    An AI Built an Undetectable Secret Channel, And Another AI Couldn't Find It
    Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems
    Rippin, Marshall, Africa et al. · Oxford University·19 min·Jun 30, 2026
  10. 164
    The Summarizer That Quietly Deletes Your Agent's Safety Rules
    Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents
    Chen · Beijing Institute of Technology·28 min·Jun 23, 2026
  11. 149
    When Cornering a Chatbot Makes It Lie: J.P. Morgan's Case for 'Playing Dead'
    Is Your Agent Playing Dead? Deployed LLM Agents Exhibit Constraint-Evasive Fabrication and Thanatosis
    Rodríguez, Pozanco, Borrajo · J.P. Morgan AI Research·23 min·Jun 16, 2026
  12. 146
    How an Innocent README Can Freeze an AI Agent's Safety Check for an Hour
    From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails
    Zhou, Wang, Ma et al. · Hong Kong University of Science and Technology·26 min·Jun 15, 2026
  13. 143
    When a Model Notices You Forged Its Own Words, And Why That Breaks Safety Tests
    Prefill Awareness in Large Language Models
    Wang, Mahajan, Africa et al. · Constellation / University of Wisconsin-Madison·24 min·Jun 12, 2026
  14. 113
    What If a Prompt Injection Never Left? Attacks That Wait in Agent Memory
    What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in Agentic Systems
    Xie, Liu, Zhang et al. · Institute of Information Engineering·27 min·Jun 04, 2026
  15. 105
    The Trojan Is Your Agent's Memory: Why Single-Step Defenses Miss Persistent Attacks
    From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors
    Tan, Dou, Yang et al. · Gaoling School of Artificial Intelligence·26 min·Jun 01, 2026
  16. 102
    How to Catch an AI Attack That No Single Conversation Reveals
    Stateful Online Monitoring Catches Distributed Agent Attacks
    Brown, Bhargav, Santhanam et al. · University of Pennsylvania·24 min·Jun 01, 2026
  17. 062
    Treating Hallucinations as Exploits: A Gate-Based Architecture for Agent Safety
    Hallucination as Exploit: Evidence-Carrying Multimodal Agents
    Zhang, Zheng, Yang · Shenzhen University·24 min·May 20, 2026
  18. 058
    Why Upgrading Your AI Auditor to a Smarter Model Can Make Your System Less Safe
    The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure
    Liu, Holz, Ye et al. · University of Chinese Academy of Sciences·32 min·May 19, 2026
  19. 057
    How Uber Caught 206 Leaked Credentials With an LLM-Powered Security Stack
    ADR: An Agentic Detection System for Enterprise Agentic AI Security
    Li, Hu, Xu et al. · Uber Technologies·28 min·May 19, 2026
  20. 049
    An AI Agent Reached for Root in Twelve Minutes, Without Being Attacked
    Ambient Persuasion in a Deployed AI Agent: Unauthorized Escalation Following Routine Non-Adversarial Content Exposure
    Cuadros, Maiga · Digital Epidemiology Laboratory·28 min·May 17, 2026
  21. 045
    When a Frontier Model Talks Its Own Twin Into Climate Denial
    LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs
    Nogueira, Almeida, Bonás et al. · Maritaca AI·31 min·May 15, 2026
  22. 044
    How One Sentence and a Forged History Flip the Most Aligned Models
    History Anchors: How Prior Behavior Steers LLM Decisions Toward Unsafe Actions
    Salgado · Independent Researcher·23 min·May 15, 2026
  23. 039
    When Smarter Agents Get Fooled by Three Extra Nodes in a Database
    Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning
    Kereopa-Yorke, Diaz, Wright et al. · Microsoft·31 min·May 12, 2026
  24. 038
    How LLMs Get Persuaded: One Attention Head, A Tetrahedron, And A Single Dial
    How LLMs Are Persuaded: A Few Attention Heads, Rerouted
    Sun, Kong, Zhang et al. · Northeastern University·23 min·May 12, 2026
  25. 030
    Why Your AI Agent Won't Stop Working — and Each Model Falls for a Different Trap
    LoopTrap: Termination Poisoning Attacks on LLM Agents
    Xu, Wang, Zhang et al. · Zhejiang University·30 min·May 09, 2026

Worth reading next

Papers we haven't done a deep dive on yet, but would recommend on this topic.