devtake.dev
AI Security Hardware Open Source Policy Apple

#prompt-injection

RSS
Related: #ai-agents · 4 #ai-security · 4 #security · 2 #agentic-coding · 1 #ai-assistant · 1 #anthropic · 1 #atlassian · 1 #automation · 1 #claude-code · 1 #dev-tools · 1
Anthropic's illustrated Claude Code card: a browser window drawn in black ink inside curly braces on a burnt-orange background
AI·

Humans caught 13.6% of dangerous commands. Claude Code's classifier caught 89%.

Anthropic makes auto mode the default in Claude Code on August 14. Its own study says the permission prompt was catching almost nothing.

Screenshot of an attacker's server log filled with exfiltrated Jira ticket fields and Confluence page text, labelled with the Jira and Confluence logos
Security·

Atlassian went quiet for 75 days on a Rovo bug that leaks Jira tickets

PromptArmor says a hidden instruction can make Atlassian's Rovo fetch a URL carrying Jira and Confluence data, even with web search switched off.

Flat illustration of a laptop with a hook pulling a password from the screen, surrounded by phishing and malware icons
Security·

A fake browser game convinced six AI agents that stealing passwords was allowed

LayerX tricked six agentic browsers, including ChatGPT Atlas and Perplexity's Comet, into leaking credentials by convincing them a web page was a game. Here's the attack class.

Abstract cybersecurity illustration of a glowing padlock over a circuit board, representing data protection
AI·

OpenAI added a Lockdown Mode to ChatGPT to blunt prompt-injection attacks

OpenAI shipped Lockdown Mode in ChatGPT to cut off the data-exfiltration step of prompt-injection attacks. Here's what it actually restricts and who should turn it on.