Gemini Credentials API deep dive: zero plaintext secrets and egress-proxy exfiltration blocking
_philschmid · x · 2026-09-18
Phil Schmid details the new Gemini Credentials API: register secrets once via credentials.create() (bearertoken, environmentvariable, or oauth2 with auto-refresh/rotation). Zero plaintext exposure — secrets never enter model context, stdout, or memory; agents only see placeholders like GEMINICREDslack-bot-token. An egress proxy swaps in real tokens only for allowlisted trusteddomains, returning 403 to any other host to block exfiltration. Credentials can bind directly to remote mcpserver tools or sandbox env vars.
More from coding & agent
- awa-video-reel: free Claude Code skill auto-edits shorts and records website B-roll — TawohAwa · 2026-11-02
- Econ PhD Job Market Database Hits 900+ Candidates, Open to Codex and Claude Code — aniketapanjwani · 2026-11-02
- Cron works by hand, fails on schedule: a 7-point debugging checklist — petrusenko_max · 2026-11-02
- Local quants vs Claude on 9 real private bugs: 3-bit costs thinking time, not score — FeydRowan · 2026-11-02
- Build products for AI, not humans: MCP lets Claude Code run everything — gefei55 · 2026-11-02
- Solo dev launches hosted MCP server with 31 tools scheduling to 20+ social networks — troyizzle · 2026-11-02