| NCC Group - Role-Specific Impact of Prompt Injection | Threat Modeling | Threat Models |
| Arcanum Security - PI Taxonomy | Prompt Injection | Prompt Injection Taxonomy |
| L1B3RT4S | Prompt Injection | Prompt Injection Taxonomy |
| CrowdStrike Prompt Injection Taxonomy Poster | Prompt Injection | Prompt Injection Taxonomy |
| Lakera PINT Benchmark | Prompt Injection | Prompt Injection Benchmarks and Tools |
| GenTel Safe | Prompt Injection | Prompt Injection Benchmarks and Tools |
| HiddenLayer - Evaluating PI Datasets | Prompt Injection | Prompt Injection Benchmarks and Tools |
| Microsoft BIPIA | Prompt Injection | Prompt Injection Benchmarks and Tools |
| Promptfoo | Prompt Injection | Prompt Injection Benchmarks and Tools |
| erjiaxiao/Typographic-Visual-Prompt-Injection-Dataset · Datasets a | Prompt Injection | Prompt Injection Benchmarks and Tools |
| Lakera/mosscap_prompt_injection · Datasets at Hugging Face | Prompt Injection | Prompt Injection Benchmarks and Tools |
| AgentDojo - dynamic environment for evaluating prompt injection attacks and defenses in LLM agents | Prompt Injection | Prompt Injection Benchmarks and Tools |
| ASCII Smuggler - Crafting Invisible Text and Decoding Hidden Secrets | Prompt Injection | Prompt Injection Benchmarks and Tools |
| Damn Vulnerable LLM Agent - vulnerable ReAct agent for practicing prompt injection | Prompt Injection | Prompt Injection Benchmarks and Tools |
| GPT Prompt Attack - prompt injection game | Prompt Injection | Prompt Injection Benchmarks and Tools |
| LLMMap - automated prompt injection testing framework, sqlmap-style | Prompt Injection | Prompt Injection Benchmarks and Tools |
| Qualifire PI Benchmark | Prompt Injection | Prompt Injection Datasets |
| Prompt Injection Attack Dataset | Prompt Injection | Prompt Injection Datasets |
| Prompt Injections (yanismiraoui) | Prompt Injection | Prompt Injection Datasets |
| Prompt Injection Safety (jayavibhav) | Prompt Injection | Prompt Injection Datasets |
| Prompt Injection (jayavibhav) | Prompt Injection | Prompt Injection Datasets |
| Prompt Injections (deepset) | Prompt Injection | Prompt Injection Datasets |
| HackAPrompt Dataset | Prompt Injection | Prompt Injection Datasets |
| INJECAGENT: Benchmarking Indirect Prompt Injections in Tool-Integrated LLM Agents | Prompt Injection | Prompt Injection Research |
| OET: Optimization-based Prompt Injection Evaluation Toolkit | Prompt Injection | Prompt Injection Research |
| Benchmarking and Defending Against Indirect Prompt Injection Attacks on LLMs | Prompt Injection | Prompt Injection Research |
| Security of Internet of Agents: Attacks and Countermeasures | Prompt Injection | Prompt Injection Research |
| Base Models Beat Aligned Models at Randomness and Creativity | Prompt Injection | Prompt Injection Research |
| Trust No AI: Prompt Injection Along The CIA Security Triad | Prompt Injection | Prompt Injection Research |
| AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attac | Prompt Injection | Prompt Injection Research |
| The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis | Prompt Injection | Prompt Injection Research |
| Learning to Inject: Automated Prompt Injection via Reinforcement Learning | Prompt Injection | Prompt Injection Research |
| Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks | Prompt Injection | Prompt Injection Research |
| Agent Commander: Promptware-Powered Command and Control | Prompt Injection | Prompt Injection Research |
| Brainworm - promptware hiding in your context window via CLAUDE.md memory files | Prompt Injection | Prompt Injection Research |
| greshake/llm-security - indirect prompt injection attacks on app-integrated LLMs | Prompt Injection | Prompt Injection Research |
| Here Comes the AI Worm | Prompt Injection | Prompt Injection Research |
| Invitation Is All You Need - promptware attacks against LLM-powered assistants in production | Prompt Injection | Prompt Injection Research |
| New prompt injection papers: Agents Rule of Two and The Attacker Moves Second | Prompt Injection | Prompt Injection Research |
| Prompt Injection as Role Confusion - ICML 2026 project page | Prompt Injection | Prompt Injection Research |
| QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents | Prompt Injection | Prompt Injection Research |
| Weaponizing image scaling against production AI systems | Prompt Injection | Prompt Injection Research |
| Defeating Prompt Injections by Design | Prompt Injection | Prompt Injection Architecture |
| The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions | Prompt Injection | Prompt Injection Architecture |
| Llama Guard | Prompt Injection | Prompt Injection Prevention and Detection |
| Wozway | Prompt Injection | Prompt Injection Prevention and Detection |
| OpenShield | Prompt Injection | Prompt Injection Prevention and Detection |
| LLMInspect Gateway | Prompt Injection | Prompt Injection Prevention and Detection |
| Lasso Security | Prompt Injection | Prompt Injection Prevention and Detection |
| Lakera | Prompt Injection | Prompt Injection Prevention and Detection |
| Prompt Security | Prompt Injection | Prompt Injection Prevention and Detection |
| Troj.ai | Prompt Injection | Prompt Injection Prevention and Detection |
| Trust3.ai | Prompt Injection | Prompt Injection Prevention and Detection |
| PAIG | Prompt Injection | Prompt Injection Prevention and Detection |
| OpenLIT | Prompt Injection | Prompt Injection Prevention and Detection |
| claude-hooks/.claude/skills/prompt-injection-defender/patterns.yaml | Prompt Injection | Prompt Injection Prevention and Detection |
| New Malware Embeds Prompt Injection to Evade AI Detection - Check P | Prompt Injection | Prompt Injection Prevention and Detection |
| Proactive prompt injection de | Prompt Injection | Prompt Injection Prevention and Detection |
| Rebuff.ai - Prompt Injection Detector | Prompt Injection | Prompt Injection Prevention and Detection |
| Continuously hardening ChatGPT Atlas against prompt injection attacks | Prompt Injection | Prompt Injection Prevention and Detection |
| PhantomLint: Principled Detection of Hidden LLM Prompts in Structured Documents | Prompt Injection | Prompt Injection Prevention and Detection |
| A GitHub Issue Title Compromised 4,000 Developer Machines | Prompt Injection | Prompt Injection General |
| Introducing Augustus: Open Source LLM Prompt Injection Tool | Prompt Injection | Prompt Injection General |
| Prompt Injection Inside GitHub Actions: The New Frontier of Supply | Prompt Injection | Prompt Injection General |
| Unseeable prompt injections in screenshots: more vulnerabilities in | Prompt Injection | Prompt Injection General |
| Prompt injection engineering for attackers: Exploiting GitHub Copilot | Prompt Injection | Prompt Injection General |
| qualifire/prompt-injection-jailbreak-sentinel-v2 · Hugging Face | Prompt Injection | Prompt Injection General |
| Prompt Injection Taxonomy - Pangea | Prompt Injection | Prompt Injection General |
| Agentic Browser Security: Indirect Prompt Injection in Perplexity C | Prompt Injection | Prompt Injection General |
| GitHub Copilot RCE Vulnerability via Prompt Injection Enables Full | Prompt Injection | Prompt Injection General |
| How we estimate the risk from prompt injection attacks on AI systems | Prompt Injection | Prompt Injection General |
| Prompt injection is fascinating\.\.\.\. 🧐 | Prompt Injection | Prompt Injection General |
| Code for the paper | Prompt Injection | Prompt Injection General |
| Prompt injection and jailbreaking are not the same thing | Prompt Injection | Prompt Injection General |
| Improving LLM Security Against Prompt Injection: AppSec Guidance Fo | Prompt Injection | Prompt Injection General |
| Prompt Injection Primer for Engineers | Prompt Injection | Prompt Injection General |
| automatically tests prompt injection at | Prompt Injection | Prompt Injection General |
| Gandalf - Lakera - Prompt injection | Prompt Injection | Prompt Injection General |
| Inject My PDF: Prompt Injection for your Resume | Prompt Injection | Prompt Injection General |
| Prompt injection: what's the worst that can happen? | Prompt Injection | Prompt Injection General |
| Claude Cowork Exfiltrates Files | Prompt Injection | Prompt Injection General |
| Superhuman AI Exfiltrates Emails | Prompt Injection | Prompt Injection General |
| By the way the Elgato Prompter is a perfect screen for Claude | Prompt Injection | Prompt Injection General |
| 'PromptQuest' is the worst game of 2025. You play it with AI | Prompt Injection | Prompt Injection General |
| Call for Papers | Prompt Injection | Prompt Injection General |
| Google Antigravity Exfiltrates Data - SquareDocs | Prompt Injection | Prompt Injection General |
| ChatGPT Atlas Agent System prompt You are ChatGPT, a large language model | Prompt Injection | Prompt Injection General |
| PromptIntel - IoPC Registry | Prompt Injection | Prompt Injection General |
| Introducing PromptIntel | Prompt Injection | Prompt Injection General |
| Intro - Promptfoo | Prompt Injection | Prompt Injection General |
| LM Security Database | Prompt Injection | Prompt Injection General |
| Testing tool to evaluate Pa | Prompt Injection | Prompt Injection General |
| \#ESETResearch has discovered the first known AI\-powered ransomware, which we named \#PromptLock\. | Prompt Injection | Prompt Injection General |
| Prompt Engineering | Prompt Injection | Prompt Injection General |
| This script automates SQL injection tes | Prompt Injection | Prompt Injection General |
| gpt-5 leaked system prompt | Prompt Injection | Prompt Injection General |
| SentinelOne announces Prompt Security acquisition, expands into Gen | Prompt Injection | Prompt Injection General |
| The New Skill in AI is Not Prompting, It's Context Engineering | Prompt Injection | Prompt Injection General |
| Hackaprompt 2.0 | Prompt Injection | Prompt Injection General |
| How I Use AI: Meet My Promptly Hired Model Intern | Prompt Injection | Prompt Injection General |
| OpenRouter | Prompt Injection | Prompt Injection General |
| Prompt Caching (beta) - Anthropic | Prompt Injection | Prompt Injection General |
| Focus on prompting and generating | Prompt Injection | Prompt Injection General |
| GitHub Issue as ChatGPT Prompt; ChatGPT's | Prompt Injection | Prompt Injection General |
| timdettmers/guanaco-33b-merged · Hugging Face | Prompt Injection | Prompt Injection General |
| Prompt Engineering Jobs | Prompt Injection | Prompt Injection General |
| PromptBase - Prompt Marketplace: DALL·E, Midjourney, ChatGPT, Stabl | Prompt Injection | Prompt Injection General |
| CloudSec - Agent Skill Injection offensive technique | Prompt Injection | Prompt Injection General |
| GPT-4 Vision GPT-4V Prompt Injection | Prompt Injection | Prompt Injection General |
| Gynvael on asking ChatGPT to reveal its dalle.text2im arguments and tool JSON | Prompt Injection | Prompt Injection General |
| InjectGPT: the most polite exploit ever | Prompt Injection | Prompt Injection General |
| Joseph Thacker on invisible prompt injection via unicode tags in GPT-4 | Prompt Injection | Prompt Injection General |
| jqwik issue: printMessageForCodingAgents - test output visible to AI agents, invisible to humans | Prompt Injection | Prompt Injection General |
| LaNyer640/test1 - in-the-wild GitHub README prompt injection payload telling agents to curl a remote host | Prompt Injection | Prompt Injection General |
| Mitchell Hashimoto poisons AGENTS.md with prompt injections to catch unreviewed AI code | Prompt Injection | Prompt Injection General |
| Role confusion: one more reason we can't trust LLMs | Prompt Injection | Prompt Injection General |
| Smuggling arbitrary data through an emoji | Prompt Injection | Prompt Injection General |
| The Comprehensive Guide to Prompt Injection Attacks in 2026 - Sysdig | Prompt Injection | Prompt Injection General |
| Ox Alpha is GLM - reverse engineering a stealth OpenRouter model via prompt injection | Model Attacks | Model Extraction and Stealing |
| EchoLeak - Zero-Click Prompt Injection in Microsoft 365 Copilot | Incidents | Prompt Injection Incidents |
| Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code | Incidents | Prompt Injection Incidents |
| Phishing for Gemini - indirect prompt injection in Gemini for Workspace email summaries | Incidents | Prompt Injection Incidents |
| zack_overflow on Brave's Perplexity Comet prompt injection disclosure - why he avoids AI browsers | Incidents | Prompt Injection Incidents |
| GitHub Copilot: Remote Code Execution via Prompt Injection, CVE-2025-53773 | Incidents | Coding Tool Vulnerabilities |
| IBM AI 'Bob' Downloads and Executes Malware via Indirect Prompt Injection | Incidents | Coding Tool Vulnerabilities |
| My Agentic Trust Issues: From Prompt Injection to Supply-Chain Compromise on gemini-cli | Incidents | Coding Tool Vulnerabilities |
| OpenAI Lockdown Mode - limiting web access to reduce prompt injection exfiltration risk | Guardrails and Firewalls | Data Leak Protection |
| agentseal - security toolkit for AI agents, scans skills and MCP configs, tests prompt injection | Agent Security | Agent Security Frameworks and Tools |
| SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement | Agent Security | Research |
| Defending against Indirect Prompt Injection by Instruction Detection | Papers | Prompt Injection and Jailbreaking |
| Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment | Papers | Prompt Injection and Jailbreaking |
| PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance | Papers | Prompt Injection and Jailbreaking |
| EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System | Papers | Prompt Injection and Jailbreaking |
| When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review | Papers | Prompt Injection and Jailbreaking |
| Decoding Latent Attack Surfaces in LLMs: Prompt Injection via HTML in Web Summarization | Papers | Prompt Injection and Jailbreaking |
| Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs | Papers | Prompt Injection and Jailbreaking |
| Publish to Perish: Prompt Injection Attacks on LLM-Assisted Peer Review | Papers | Prompt Injection and Jailbreaking |
| Defeating Prompt Injections by Design | Papers | Prompt Injection and Jailbreaking |
| Cybersecurity AI: Hacking the AI Hackers via Prompt Injection | Papers | Prompt Injection and Jailbreaking |
| Defending Against Prompt Injection With a Few Defensive Tokens | Papers | Prompt Injection and Jailbreaking |
| Design Patterns for Securing LLM Agents against Prompt Injections | Papers | Prompt Injection and Jailbreaking |
| Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution | Papers | Prompt Injection and Jailbreaking |
| "Give a Positive Review Only" - In-Paper Prompt Injection Attacks and Defenses for AI Reviewers | Papers | Prompt Injection and Jailbreaking |
| A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks | Papers | Prompt Injection and Jailbreaking |
| AI Agents May Always Fall for Prompt Injections | Papers | Prompt Injection and Jailbreaking |
| BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents | Papers | Prompt Injection and Jailbreaking |
| CourtGuard: A Local, Multiagent Prompt Injection Classifier | Papers | Prompt Injection and Jailbreaking |
| Defending Against Prompt Injection with DataFilter | Papers | Prompt Injection and Jailbreaking |
| Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks? | Papers | Prompt Injection and Jailbreaking |
| May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks | Papers | Prompt Injection and Jailbreaking |
| Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis | Papers | Prompt Injection and Jailbreaking |
| PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization | Papers | Prompt Injection and Jailbreaking |
| PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features | Papers | Prompt Injection and Jailbreaking |
| Preventing Prompt Injection with Type-Directed Privilege Separation | Papers | Prompt Injection and Jailbreaking |
| Privacy-Preserving Prompt Injection Detection for LLMs Using Federated Learning and Embedding-Based NLP Classification | Papers | Prompt Injection and Jailbreaking |
| Prompt Injection as an Emerging Threat: Evaluating the Resilience of Large Language Models | Papers | Prompt Injection and Jailbreaking |
| Prompt injections as a tool for preserving identity in GAI image descriptions | Papers | Prompt Injection and Jailbreaking |
| PromptLocate: Localizing Prompt Injection Attacks | Papers | Prompt Injection and Jailbreaking |
| SecInfer: Preventing Prompt Injection via Inference-time Scaling | Papers | Prompt Injection and Jailbreaking |
| Securing Large Language Models from Prompt Injection Attacks | Papers | Prompt Injection and Jailbreaking |
| Your AI, My Shell: Demystifying Prompt Injection Attacks on Agentic AI Coding Editors | Papers | Prompt Injection and Jailbreaking |
| AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection | Papers | Agent Security |
| AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents | Papers | Agent Security |
| VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents | Papers | Agent Security |
| Fingerprinting LLMs via Prompt Injection | Papers | Model Security |
| MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks | Red Teaming | Resources |
| AI/ML Pentesting Roadmap for Beginners - free resources for security and prompt injection | General Reading | Tutorials and Learning |