malicious instructions – Experimental News Clipping Site

Simon Willison’s Weblog: Embracing the parallel coding agent lifestyle

Oct 5, 2025

—

by

Source URL: https://simonwillison.net/2025/Oct/5/parallel-coding-agents/ Source: Simon Willison’s Weblog Title: Embracing the parallel coding agent lifestyle Feedly Summary: For a while now I’ve been hearing from engineers who run multiple coding agents at once – firing up several Claude Code or Codex CLI instances at the same time, sometimes in the same repo, sometimes against multiple checkouts…

Simon Willison’s Weblog: Designing agentic loops

Sep 30, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Sep/30/designing-agentic-loops/ Source: Simon Willison’s Weblog Title: Designing agentic loops Feedly Summary: Coding agents like Anthropic’s Claude Code and OpenAI’s Codex CLI represent a genuine step change in how useful LLMs can be for producing working code. These agents can now directly exercise the code they are writing, correct errors, dig through existing implementation…

Schneier on Security: Abusing Notion’s AI Agent for Data Theft

Sep 29, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://www.schneier.com/blog/archives/2025/09/abusing-notions-ai-agent-for-data-theft.html Source: Schneier on Security Title: Abusing Notion’s AI Agent for Data Theft Feedly Summary: Notion just released version 3.0, complete with AI agents. Because the system contains Simon Willson’s lethal trifecta, it’s vulnerable to data theft though prompt injection. First, the trifecta: The lethal trifecta of capabilities is: Access to your private…

Simon Willison’s Weblog: ForcedLeak: AI Agent risks exposed in Salesforce AgentForce

Sep 26, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Sep/26/agentforce/#atom-everything Source: Simon Willison’s Weblog Title: ForcedLeak: AI Agent risks exposed in Salesforce AgentForce Feedly Summary: ForcedLeak: AI Agent risks exposed in Salesforce AgentForce Classic lethal trifecta image exfiltration bug reported against Salesforce AgentForce by Sasi Levi and Noma Security. Here the malicious instructions come in via the Salesforce Web-to-Lead feature. When a…

Simon Willison’s Weblog: Claude API: Web fetch tool

Sep 10, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Sep/10/claude-web-fetch-tool/#atom-everything Source: Simon Willison’s Weblog Title: Claude API: Web fetch tool Feedly Summary: Claude API: Web fetch tool New in the Claude API: if you pass the web-fetch-2025-09-10 beta header you can add {“type": "web_fetch_20250910", "name": "web_fetch", "max_uses": 5} to your "tools" list and Claude will gain the ability to fetch content from…

Simon Willison’s Weblog: My review of Claude’s new Code Interpreter, released under a very confusing name

Sep 9, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://simonwillison.net/2025/Sep/9/claude-code-interpreter/ Source: Simon Willison’s Weblog Title: My review of Claude’s new Code Interpreter, released under a very confusing name Feedly Summary: Today on the Anthropic blog: Claude can now create and edit files: Claude can now create and edit Excel spreadsheets, documents, PowerPoint slide decks, and PDFs directly in Claude.ai and the desktop…

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

Sep 1, 2025

—

by

Kurt Seifried

in Uncategorized

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…

Tag: malicious instructions