Analysis

Sharing secrets with LLM agents

Page published

Publication date unknown · First observed: 18 Nov 2026

Coverage timeline

18 Nov 2026vepsala.devobserved

Single-source analysis — one report is available.

Why it matters

Coding agents can expose reachable credentials even when secrets never enter the conversation, so keeping keys out of prompts alone does not prevent theft.

“Sharing secrets with LLM agents” examines how coding agents can expose credentials through both their conversation context and their execution environment. The article discusses prompt injection, malicious dependencies, compromised tools and model infrastructure, arguing against running agents directly on a credential-rich main operating system.