HackerTrans
トップ新着トレンドコメント過去質問紹介求人

saranshrana

no profile record

投稿

Show HN: Burrow – Runtime Security for AI Agents

3 ポイント·投稿者 saranshrana·3 か月前·0 コメント

Ask HN: How are you handling runtime security for your AI agents?

2 ポイント·投稿者 saranshrana·3 か月前·2 コメント

コメント

saranshrana
·3 か月前·議論
Honestly, best solution is to use native CSP solutions like AWS Secrets Manager, AWS SSM Parameter Store, GCP Secret Manager, Terraform Vault.

All these have native audit logs and access logs, which can help you pin point exactly when did your AI Agent requested and accessed your secrets at Runtime.
saranshrana
·3 か月前·議論
[dead]
saranshrana
·3 か月前·議論
Runtime Security for AI Agents and Co-Pilots

Try it here - https://burrow.run/
saranshrana
·3 か月前·議論
Interesting work, just curious, are you defining Agent Identity at the MCP layer itself ?

assuming "SessionID" -> Agent Identity (Randomised) ?