Skyflow interceptor de-identifies agent tool calls on Bedrock AgentCore Gateway
AWS ML Blog · rss · 2026-11-20
An AWS ML Blog post shows how to keep sensitive data out of agent tool calls and model context by attaching Skyflow Detect as request/response interceptors on Amazon Bedrock AgentCore Gateway. It addresses three gaps: sensitive values leaking through tool arguments, personal data returning in tool results, and document tools bypassing text inspection via signed URLs. Three modes — Shield the tool (reversible vault tokens), Shield the model (de-identify everything the model reads), Shield the document (swap URLs for cleaned copies) — apply per tool without changing agent or tool code. Production features include no-redeploy policy config via Parameter Store, fail-closed behavior, Secrets Manager key storage and CloudWatch audit logging, demonstrated through a European bank's dispute-resolution agent.
More from coding & agent
- TestSprite 4.0 launches as an independent test layer for AI-written code — Tegadesigns · 2026-11-20
- VP of engineering: coding models report like bad direct reports — raw dumps, no TLDR — robleclerc · 2026-11-20
- Lawyer runs full DeepSeek-V4.1-Flash on 12x V100 at 157-184 tok/s, beating DGX Spark stacks — TumbleweedNew6515 · 2026-11-20
- GitHub open-sources Agent Host Protocol for cross-device agent sessions — rseroter · 2026-11-20
- 100% code-driven Blender squirrel film, made for $34.76 — no video gen models — dreamwieber · 2026-11-20
- How Cisco upskilled 1,200 engineers in agentic AI via AWS AI League tournaments — AWS ML Blog · 2026-11-20