Safer coding agents: synthetic credentials via 1Password intercepting proxy
craigbalding · x · 2026-11-18
Many want to run coding agents but hesitate to hand over passwords. The author shares two "Safeyolo" tactics:
- Issue agents synthetic credentials and swap them upstream for real ones via an intercepting HTTPS proxy wired into 1Password;
- Block agents from reaching any endpoint where they could change passwords or escalate privileges.
The core idea: real credentials never enter the agent's context, and self-privilege-escalation paths are cut off.
More from coding & agent
- Which web search API do you actually use for agents? Exa, Tavily, Brave compared — Fluffy-Resident-8734 · 2026-11-18
- Devs reportedly push thousands of unchecked lines daily to prod to hit AI-driven KPIs — HildeKuehne · 2026-11-18
- AI short film workflow revealed: Seedance 2.5, Kling 4.0, Nano Banana, Suno, Premiere — Uncanny_Harry · 2026-11-18
- Microsoft adds role-based Copilot skills as Agent 365 passes 50 million agents — shashib · 2026-11-18
- philschmid: replace built-in multi-agent features with an MCP server of the harness itself — _philschmid · 2026-11-18
- Running multiple LLM agents 24/7 on a VPS: why Telegram management falls apart — thetapereader · 2026-11-18