121–130 of 290 posts
OpenAI should probably consider: - enabling local MCP in Desktop like Claude Desktop, not just server-side remote. (I don't think you can run a local server unless you expose it to their IP) - having an MCP store where you can click on e.g. Figma to connect your account and start talking to it - letting you easily connect to your own Agents SDK MCP servers deployed in their cloud ChatGPT MCP support is underwhelming…
Earlier quoted context omitted.
The solution is to sanitize text that goes into the prompt by creating a neural network that can detect prompts
Isn't that just another guardrail that can be bypassed much the same as the guard rails are currently quite easily bypassed? It is not easy to detect a prompt. Note some of the recent prompt injection attack where the injection was a base64 encoded string hidden deep within an otherwise accurate logfile. The LLM, while seeing the Jira ticket with attached trace , as part of the analysis decided to decode the b64 and…
The same AI companies: here's a way to give AI full executable access to your personal data, enjoy!
Earlier quoted context omitted.
IMO the way we need to be thinking about prompt injection is that any tool can call any other tool. When introducing a tool with untrusted output (that is to say, pretty much everything, given untrusted input) you’re exposing every other tool as an attack vector. In addition the LLMs themselves are vulnerable to a variety of attacks. I see no mention of prompt injection from Anthropic or OpenAI in their announcements…
Anthropic talked about prompt injection a bunch in the docs for their web fetch tool feature they released today: https://docs.anthropic.com/en/docs/agents-and-tools/tool-use... My notes: https://simonwillison.net/2025/Sep/10/claude-web-fetch-tool/
Earlier quoted context omitted.
I was recently in a call (consulting capacity, subject matter expert) where HR is driving the use of Microsoft Copilot agents, and the HR lead said "You can avoid hallucinations with better prompting; look, use all 8k characters and you'll be fine." Please, proceed. Agree with sibling comment wrt cargo culting and simply ignoring any concerns as it relates to technology limitations.
The solution is to sanitize text that goes into the prompt by creating a neural network that can detect prompts
LLMs making arbitrary real-world actions via MCP.
What could possibly go wrong?
Only the good guys are going to get this, right?
Earlier quoted context omitted.
I still don't understand understand. Aren't the risks the exact same for any external facing API? Maybe my imagined use case for MCP servers is different from others.
Imagine running an MCP server inside your network that grants you access to some internal databases. You might expect this to be safe but once you connect that internal MCP server to an AI agent all bets are off. It could be something as simple as the AI agent offering to search the Internet but being convinced to embed information provided from your internal MCP server into the search query for a public (or adversar…
Wow this is dangerous. I wonder how many people are going to turn this on without understanding the full scope of the risks it opens them up to. It comes with plenty of warnings, but we all know how much attention people pay to those. I'm confident that the majority of people messing around with things like MCP still don't fully understand how prompt injection attacks work and why they are such a significant threat.