hard20 pts · first answer countsllm-safetyjailbreaks
Letting users write the assistant turn
Your public API passes user-supplied messages straight to the model, including any "assistant" role messages they send. Why is this risky?
Discussion 0
Join free to post in the discussion.
Related questions
- Jailbreak or prompt injectionPrompt Engineer
- Customer data in promptsPrompt Engineer
- Top risk in the OWASP LLM listPrompt Engineer
- What "guardrails" meansPrompt Engineer
- Checking before and after the modelPrompt Engineer
- Tool access for an FAQ botPrompt Engineer
- Calling the LLM from the browserPrompt Engineer
- One user sending 50,000 requestsPrompt Engineer