malicious instructions – Experimental News Clipping Site

The Register: LegalPwn: Tricking LLMs by burying badness in lawyerly fine print

Sep 1, 2025

—

by

Source URL: https://www.theregister.com/2025/09/01/legalpwn_ai_jailbreak/ Source: The Register Title: LegalPwn: Tricking LLMs by burying badness in lawyerly fine print Feedly Summary: Trust and believe – AI models trained to see ‘legal’ doc as super legit Researchers at security firm Pangea have discovered yet another way to trivially trick large language models (LLMs) into ignoring their guardrails. Stick…

Simon Willison’s Weblog: Agentic Browser Security: Indirect Prompt Injection in Perplexity Comet

Aug 25, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Aug/25/agentic-browser-security/#atom-everything Source: Simon Willison’s Weblog Title: Agentic Browser Security: Indirect Prompt Injection in Perplexity Comet Feedly Summary: Agentic Browser Security: Indirect Prompt Injection in Perplexity Comet The security team from Brave took a look at Comet, the LLM-powered “agentic browser" extension from Perplexity, and unsurprisingly found security holes you can drive a truck…

Embrace The Red: Sneaking Invisible Instructions by Developers in Windsurf

Aug 24, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://embracethered.com/blog/posts/2025/windsurf-sneaking-invisible-instructions-for-prompt-injection/ Source: Embrace The Red Title: Sneaking Invisible Instructions by Developers in Windsurf Feedly Summary: Imagine a malicious instruction hidden in plain sight, invisible to you but not to the AI. This is a vulnerability discovered in Windsurf Cascade, it follows invisible instructions. This means there can be instructions in a file or…

Simon Willison’s Weblog: The Summer of Johann: prompt injections as far as the eye can see

Aug 15, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Aug/15/the-summer-of-johann/#atom-everything Source: Simon Willison’s Weblog Title: The Summer of Johann: prompt injections as far as the eye can see Feedly Summary: Independent AI researcher Johann Rehberger has had an absurdly busy August. Under the heading The Month of AI Bugs he has been publishing one report per day across an array of different…

Simon Willison’s Weblog: When a Jira Ticket Can Steal Your Secrets

Aug 9, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Aug/9/when-a-jira-ticket-can-steal-your-secrets/ Source: Simon Willison’s Weblog Title: When a Jira Ticket Can Steal Your Secrets Feedly Summary: When a Jira Ticket Can Steal Your Secrets Zenity Labs describe a classic lethal trifecta attack, this time against Cursor, MCP, Jira and Zendesk. They also have a short video demonstrating the issue. Zendesk support emails are…

Simon Willison’s Weblog: My Lethal Trifecta talk at the Bay Area AI Security Meetup

Aug 9, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Aug/9/bay-area-ai/#atom-everything Source: Simon Willison’s Weblog Title: My Lethal Trifecta talk at the Bay Area AI Security Meetup Feedly Summary: I gave a talk on Wednesday at the Bay Area AI Security Meetup about prompt injection, the lethal trifecta and the challenges of securing systems that use MCP. It wasn’t recorded but I’ve created…

Simon Willison’s Weblog: Quoting @himbodhisattva

Aug 4, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Aug/4/himbodhisattva/#atom-everything Source: Simon Willison’s Weblog Title: Quoting @himbodhisattva Feedly Summary: for services that wrap GPT-3, is it possible to do the equivalent of sql injection? like, a prompt-injection attack? make it think it’s completed the task and then get access to the generation, and ask it to repeat the original instruction? — @himbodhisattva,…

Simon Willison’s Weblog: Supabase MCP can leak your entire SQL database

Jul 6, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Jul/6/supabase-mcp-lethal-trifecta/#atom-everything Source: Simon Willison’s Weblog Title: Supabase MCP can leak your entire SQL database Feedly Summary: Supabase MCP can leak your entire SQL database Here’s yet another example of a lethal trifecta attack, where an LLM system combines access to private data, exposure to potentially malicious instructions and a mechanism to communicate data…

Simon Willison’s Weblog: The lethal trifecta for AI agents: private data, untrusted content, and external communication

Jun 16, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/#atom-everything Source: Simon Willison’s Weblog Title: The lethal trifecta for AI agents: private data, untrusted content, and external communication Feedly Summary: If you are a user of LLM systems that use tools (you can call them “AI agents" if you like) it is critically important that you understand the risk of combining tools…

Simon Willison’s Weblog: An Introduction to Google’s Approach to AI Agent Security

Jun 15, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Jun/15/ai-agent-security/#atom-everything Source: Simon Willison’s Weblog Title: An Introduction to Google’s Approach to AI Agent Security Feedly Summary: Here’s another new paper on AI agent security: An Introduction to Google’s Approach to AI Agent Security, by Santiago Díaz, Christoph Kern, and Kara Olive. (I wrote about a different recent paper, Design Patterns for Securing…

Tag: malicious instructions