HackerTrans
トップ新着トレンドコメント過去質問紹介求人

jguarnelli

no profile record

投稿

Show HN: Diplomat-agent scan Python MCP servers for unguarded tool calls

github.com
3 ポイント·投稿者 jguarnelli·17 日前·0 コメント

Show HN: Scan your AI agent's code for tool calls with no checks

github.com
2 ポイント·投稿者 jguarnelli·先月·0 コメント

Show HN: I scanned 16 AI agent repos – 76% of tool calls had no guards

github.com
1 ポイント·投稿者 jguarnelli·2 か月前·1 コメント

コメント

jguarnelli
·2 か月前·議論
[dead]
jguarnelli
·2 か月前·議論
[dead]
jguarnelli
·2 か月前·議論
What could have caused the execution to fail on the infrastructure side, regardless of what the prompt said?
jguarnelli
·2 か月前·議論
[flagged]
jguarnelli
·2 か月前·議論
[dead]
jguarnelli
·2 か月前·議論
it's a fair point sandboxing is necessary. But not sufficient for agents that legitimately need write access. A payment agent needs Stripe. A maintenance agent needs DB writes. You can't sandbox those away. The missing layer is between has access and executes
jguarnelli
·2 か月前·議論
[flagged]
jguarnelli
·2 か月前·議論
[flagged]
jguarnelli
·2 か月前·議論
[flagged]