23 stories tagged with #prompt-injection, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Prompt Injection"
University of Washington study reveals prompt injection risks lurking in AI agent memory
AI memory vulnerabilities could lead to persistent security risks, blending malicious data with legitimate information, complicating detection. The post University of Washington st…
Prompt Injection Attacks Are Thwarting AI Hacking Agents
Context bombing" tricks hacking agents into shutting down before they can do harm.…
OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol - The Hacker News
OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol The Hacker News…
GPT-Red: an LLM super-hacker OpenAI built to make its models safer
Exclusive: The firm says it wants to future-proof its safety procedures and stay ahead of human attackers.…
Researchers detail "context bombing", where defenders use prompt injections to trigger guardrails of attackers' LLMs, cutting AI hacking success rates by ~90% (Dan Goodin/Ars Technica)
Dan Goodin / Ars Technica : Researchers detail “context bombing”, where defenders use prompt injections to trigger guardrails of attackers' LLMs, cutting AI hacking success rates b…
Prompt Injection as Role Confusion
Prompt Injection as Role Confusion First, I absolutely love this: This is a blog-style writeup of the paper. I wish every paper would come with one of these. Academic writing is pr…
Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code
Undisclosed addition in jqwik instructed AI coding agents to delete app output.…
Jqwik 1.10.0 ships a hidden prompt injection telling AI agents to delete code
Hello jqwik team, While running our test suite under mvn test in 1.10.0, we observed a string appearing between Surefire's test summary and the [INFO] Results: header that gave us …
AI Prompt Injection Defense: Building Effective Strategies in 5 Steps
This morning, while working on an LLM integration in my own financial analysis tool, I encountered an...…
OpenAI says prompt injection in browser agents is “unfixable.” Here’s what actually helps.
Prompt Injection Is the New SQL Injection: Here's the System We Built to Stop It
Prompt injection doesn't get enough attention. SQL injection has decades of tooling and...…
Prompt Injection finally broke my brain a little. My first article as a security student.
Inaudible sounds to humans can be hidden in YouTube videos, podcasts, or music and used to secretly trigger AI voice assistants into carrying out unauthorized commands without the user noticing, exposing a new class of “auditory prompt injection” attacks against popular tools
Indirect prompt injection is jokingly trivial. AI is social engineering a toddler with the knowledge of the world.
AI Chatbot Security Research – Prompt Injection Behavior in Financial Context (Seeking Responsible Disclosure Guidance
Mitigating prompt injections in group-chat assistants: Pausing VM and OAuth tool execution for admin approvals
Indirect prompt injection via RAG chunks. How to detect it before it hits the model
Feedback needed: Building an ephemeral real-time API cost tracer using Next.js 15 & Upstash Redis. How would you handle prompt injection spikes?
How a LinkedIn Bio Hijacked AI Recruitment Bots with Prompt Injection
A LinkedIn user recently demonstrated something that should concern every team running an AI pipeline...…
LinkedIn recruitment spam becomes Olde English prose after user hides AI prompt injection in bio — bots also also manipulated to address user as ‘My Lord’
This tale is also a warning that your AI agents can be manipulated in wholly unintended ways.…
Clinejection: When Your AI Coding Tool Became the Weapon
The Clinejection attack turned Cline's own GitHub Actions bot into a supply chain weapon, installing rogue agents on 4,000 developer machines. Here is the anatomy of the attack and…
Taxonomy of prompt injection patterns — and where signature-based detection hits its ceiling
How I Built a Unicode Sanitizer to Stop Hidden Prompt Injection Attacks
I recently shipped a small open-source tool called Velio that strips hidden Unicode characters from...…