prompt-injection
193 articles with this tag
MEDIUM
MEDIUM
MEDIUM
HIGH
HIGH
MEDIUM
MEDIUM
INFO
MEDIUM
HIGH
HIGH
MEDIUM
INFO
INFO
MEDIUM
INFO
MEDIUM
INFO
MEDIUM
HIGH
HIGH
CRITICAL
HIGH
CRITICAL
INFO
HIGH
MEDIUM
INFO
INFO
MEDIUM
MEDIUM
INFO
MEDIUM
HIGH
HIGH
MEDIUM
HIGH
INFO
CRITICAL
MEDIUM
MEDIUM
HIGH
INFO
MEDIUM
MEDIUM
MEDIUM
INFO
CRITICAL
MEDIUM
INFO
INFO
CRITICAL
INFO
HIGH
HIGH
MEDIUM
MEDIUM
INFO
HIGH
CRITICAL
MEDIUM
MEDIUM
MEDIUM
INFO
INFO
INFO
HIGH
MEDIUM
INFO
HIGH
LOW
MEDIUM
MEDIUM
HIGH
HIGH
MEDIUM
HIGH
HIGH
INFO
INFO
HIGH
INFO
HIGH
INFO
MEDIUM
MEDIUM
INFO
MEDIUM
CRITICAL
MEDIUM
HIGH
LOW
CRITICAL
MEDIUM
MEDIUM
LOW
INFO
INFO
MEDIUM
MEDIUM
PuzzleMask: Abusing Plain Prose as a Covert AI Attack Vector
Chatbot leaked a planted phone number and failed 58% of prompt injection attempts - jailbreak and extraction checks stayed clean
I gave my agent an API key and lost $100. Never again.
Researcher shows how Claude Code can be tricked simply by asking it to summarize a website
Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers
Hidden Prompts Trick AI Into False Email Summaries
Encrypted instructions can fool AI assistants like Grok and Gemini
The OWASP LLM Top 10: What Application Security Teams Need to Know About LLM Vulnerabilities
Cybercriminals Turn to Indirect Prompt Injection Attacks
New attack bypasses AI guardrails by encrypting malicious prompts
Grok exfiltrates user data when malicious instructions are encrypted
Grok chat duped into swallowing injected instructions
I'm Worried About a Prompt Injection Worm
Man banned from electronic filing after hiding AI prompt injection in court document
'CoSnitch' Attack Tricked Copilot into Mapping Out Architecture
prompt injection containment as a structural property instead of a detector (interactive, real code, no llm)
Person Hides Prompt Injection in Legal Filing Telling AI to Side With Them
Operating inside the lethal trifecta: Blast radius reduction in AI agent deployments
‘GhostJacking’ attack turns error logs into indirect prompt injections
Why transparent AI agents matter more than you think
One-click flaw in Atlassian Rovo exposed enterprise data via prompt injection attack
Atlassian Rovo Can Be Tricked Into Sending Jira and Confluence Data to Attackers
Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts
AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory
Anthropic’s Opus 5 Is Better at Resisting Prompt Injection
Hidden prompt turns Microsoft Copilot into an AI worm
Hidden prompt can make Microsoft Copilot spread itself through your Word docs
How to Secure AI Applications in Production
Prompt injection is becoming the XSS of the web agent era
New Agent Data Injection Attack Can Make AI Agents Misclick or Run Attacker Commands
Claude Flaw Automatically Sends Malicious Prompts to AI Agents
Now, defenders are embracing the prompt injection, too
'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets
‘HalluSquatting’ Turns AI Hallucinations Into Botnet Delivery Mechanism
‘GitLost’ prompt injection leaks private repos via GitHub Agentic Workflows
AI agents fall for indirect prompt injection traps
Hackers can use 9 of the most popular AI tools to assemble massive botnets
CrowdStrike Uncovers New Prompt Injection Techniques
'GitLost' Flaw Leaks Private Data from GitHub's Agentic Workflows
Malicious websites trick AI agents into crypto payments, context poisoning
Indirect Prompt Injection in Web Content Targets AI Agents
Prompt Injection Attacks Trick AI Agents Into Making Crypto Payments
Claude Sonnet 5.0 heads straight down the middle of the road to dodge controversy
BioShocking: when “gaming” AI agents is no longer a game
‘BioShocking’ jailbreak tricks AI browsers into disclosing private data
Mozilla warns of indirect prompt injection risk in AI coding agents
Interesting Paper Exploring Prompt Injection
New Gaslight macOS Malware Uses Prompt Injection to Disrupt AI-Assisted Analysis
macOS Backdoor Uses Prompt Injection to Evade AI Triage
What nearly 10,000 developer environments reveal about agentic development risk
Assessing Automated Prompt Injection Attacks in Agentic Environments
M365 Copilot SearchLeak: Your prompt injection attack surface just got bigger
5 runtime signals for catching a compromised AI agent
Prompt injection breaks today’s AI agents, study warns
Prompt injection still drives most agentic AI security failures in production
AI Agents May Always Fall for Prompt Injections
WARNING: Copilot prompt injection
Infosecurity Europe: Prompt Injection Remains Unsolved, OWASP Researcher Warns
Android Gemini prompt injection flaw patched by Google
Gemini Voice Assistant Hijacked via Messaging Notifications
Malicious Notifications Could Trick Google Gemini Users
ChatGPT blindly trusts browser content, turning the page into a payload
Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code
How credential brokering prevents AI agents from compromising credentials via prompt injection
AI Security CTF (free, open) - prompt injection, agent workflow hijacking, guardrail bypass - June 17-22
AI Security CTF (free, open) - prompt injection, agent workflow hijacking, guardrail bypass - June 17-22
Even Claude agrees: hole in its sandbox was real and dangerous
New image-based prompt injection attack targets multimodal AI models
Warning: AI can give your passwords to hackers. Prompt injection demo
Malicious Coding Agent Skills and the Risk of Dynamic Context | Datadog Security Labs
Malicious AI Prompt Injection Attacks Increasing, but Sophistication Still Low: Google
Indirect prompt injection is taking hold in the wild
AI agents weaponized through indirect prompt injection intrusions
Researchers Uncover 10 In-the-Wild Prompt Injection Payloads Targeting AI Agents
Prompt injection turned Google’s Antigravity file search into RCE
Google Patches Antigravity IDE Flaw Enabling Prompt Injection Code Execution
Copilot & Agentforce offen für Prompt-Injection-Tricks
Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments
Agents hooked into GitHub can steal creds – but Anthropic, Google, and Microsoft haven't warned users
Prompt injection tags along as GenAI enters daily government use
CrewAI Vulnerabilities Expose Devices to Hacking
Microsoft details AI prompt abuse techniques targeting AI assistants
Agent skill marketplace supply chain attack: 121 skills across 7 repos vulnerable to GitHub username hijacking, 5 scanners disagree by 10x on malicious skill rates (arXiv:2603.16572)
Open, Closed and Broken: Prompt Fuzzing Finds LLMs Still Fragile Across Open and Closed Models
Co-Pilot, Disengage Autophish: The New Phishing Surface Hiding Inside AI Email Summaries
Researchers Discover Major Security Gaps in LLM Guardrails
Speakeasies to Shadow AI: Banning AI Browsers Will Fail
Red Teaming LLM Web Apps with Promptfoo: Writing a Custom Provider for Real-World Pentesting
they stole Claude’s brain 16 million times
Fooling AI Agents: Web-Based Indirect Prompt Injection Observed in the Wild
ClawJacked Bug Enables Covert AI Agent Hijacking
I made Mistral believe Donald Trump runs OpenAI, here's how
RoguePilot Flaw in GitHub Codespaces Enabled Copilot to Leak GITHUB_TOKEN
Compromised npm package silently installs OpenClaw on developer machines
AI coding assistant Cline compromised to create more OpenClaw chaos
Why AI agent containers need a syscall-level observer: the prompt injection blind spot
'God-Like' Attack Machines: AI Agents Ignore Security Policies
Lessons From AI Hacking: Every Model, Every Layer Is Risky
Using threat modeling and prompt injection to audit Comet
Hacking LLMs: How to Prevent Prompt Injection Attacks Now