#security

• 20 Oct 2026 · Study

  Agentic AI · Agent safety

  The main risks when agents act (prompt injection through tool outputs, excessive permissions, unconfirmed side effects) and simple defences: separating data from instructions, allow-lists, argument validation and human confirmation.

• 16 Mar 2026 · Projects

  Built this: SentinelProxy Suite

  A locally hosted HTTPS proxy and DNS server with SQLite-backed blocklists, heuristic filtering, a live WebSocket dashboard and a firewall kill switch.

• 1 Sept 2025 · Paper summary

  Paper summary: A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

  A.S.E is a repository-level benchmark for the security of AI-generated code; it finds that current LLMs still struggle with secure coding, and that a bigger reasoning budget doesn't reliably help.