We're starting to see more awareness of prompt injection as a vulnerability.
- We're starting to see more awareness of prompt injection as a vulnerability.
- Simon Willison's writeup of the EchoLeak vulnerability is worth reading.
- Notably in the Hacker News comments people are starting to realize how hard LLMs are to secure–previously I saw a lot of "that's the user's fault."
- This HackerNoon piece also points out the dangers of MCP and prompt injection.
- Another article about the dangers of MCP.
- I think we'll see many more articles about the limitations of prompt injection on systems that integrate information with AI.
- The power of integration with AI is too important, we'll have to figure out a new generalized technical approach to unlock that power responsibly![io]