medium10 pts · first answer countsllm-safetycode-executionprompt-injection
Limiting where an agent can connect
A coding agent runs in a sandbox with internet access. How do you reduce the chance that injected instructions make it upload code to an attacker's server?
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