AI News
Anthropic's Claude Cowork Now Runs Full Agentic Sessions in Chrome
The Decoder · Aug 13, 2026 · 2 min read
Anthropic just turned its Chrome extension from a research assistant into a full-fledged autonomous worker. The extensi...
Topic: prompt-injection
11 articles
Explore our coverage of prompt-injection — 11 curated articles, summaries, and related resources from the Inblix archive.
AI News
IIT Bombay's trick can rebuild your ChatGPT prompts from output alone
The Decoder · Aug 12, 2026 · 2 min read
A team from IIT Bombay and Adobe Research has cracked a problem most people assumed was practically unsolvable: reconst...
AI News
Hidden white text in a PDF can drain your Jira secrets via Atlassian's Rovo
The Decoder · Aug 10, 2026 · 2 min read
A single PDF with white-on-white text is all an attacker needs to vacuum up sensitive corporate data from Jira and Conf...
AI News
Researcher’s Copilot worm hides in Word docs and spreads unseen for 144 days
The Decoder · Aug 1, 2026 · 2 min read
Håkon Måløy didn't just find a vulnerability. He built a self-spreading worm that turns Microsoft Copilot against its u...
AI News
Anthropic's Opus 5 stopped browser prompt injections cold in 129 tests — zero successes
The Decoder · Jul 25, 2026 · 2 min read
Anthropic claims it has effectively neutralized the most persistent security headache in AI agents: prompt injection. I...
AI News
OpenAI's GPT-Red jailbreaks its own models 84% of the time
The Decoder · Jul 16, 2026 · 2 min read
OpenAI has built an AI that's better at breaking its own chatbots than any human red team ever was. The model, called G...
Product
OpenAI Trains GPT-Red to Hunt Its Own Models' Flaws
OpenAI Blog · Jul 15, 2026 · 2 min read
OpenAI has built an internal model called GPT-Red that’s designed to break other models, and they gave it an unpreceden...
Product
OpenAI's Operator can use the web for you — and that's exactly what scares its safety team
OpenAI Blog · Jul 15, 2026 · 2 min read
OpenAI just published the system card for Operator, its new Computer-Using Agent (CUA) that takes GPT-4o's vision and r...
Product
OpenAI's Deep Research Agent: Jailbreak-Resistant but Not Flawless
OpenAI Blog · Jul 14, 2026 · 3 min read
OpenAI just dropped the safety report for deep research, its new o3-powered agent that autonomously scours the web, and...
Industry
Defenders Are Now Weaponizing Prompt Injections to Trap AI Hackers
Ars Technica AI · Jul 13, 2026 · 2 min read
For years, prompt injections have been the attacker's trick — a slick way to hijack large language models into leaking...
Product
OpenAI's Plan to Stop AI From Getting Scammed Online
OpenAI Blog · Jul 12, 2026 · 2 min read
The pitch for AI agents is seductive: book my flights, find the best deal on that gadget, summarize my research. But th...