Comment by simonw
12 hours ago
Comments like this don't fill me with confidence: https://github.com/brexhq/CrabTrap/blob/4fbbda9ca00055c1554a...
// The policy is embedded as a JSON-escaped value inside a structured JSON object.
// This prevents prompt injection via policy content — any special characters,
// delimiters, or instruction-like text in the policy are safely escaped by
// json.Marshal rather than concatenated as raw text.
Why do you say that? I thought this pattern was well established, or are you aware of known issues with it?
It doesn't work. You can't trust LLMs to 100% reliably obey delimiters or structure in content. That's why prompt injection is a problem in the first place.
[dead]