# The audit log says my name: what an agent inherits when you hand it your credentials

DevFeed: [The audit log says my name: what an agent inherits when you hand it your credentials](<https://devfeed.tech/articles/the-audit-log-says-my-name-what-an-agent-inherits-when-you-hand-it-your-credentials-77481.md>)

Original publisher: [Read original article](<https://thenewstack.io/ai-agent-credential-risks/>)

Author: Naseeb Ahmed Mian

Published: 2026-10-08T15:00:00Z

Content type: article

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [Secrets Management](<https://devfeed.tech/topics/secrets-management.md>), [Secure token management](<https://devfeed.tech/topics/secure-token-management.md>), [audit](<https://devfeed.tech/topics/audit.md>), [Single sign-on (SSO)](<https://devfeed.tech/topics/sso.md>), [Secret Scanning](<https://devfeed.tech/topics/secret-scanning.md>)

Tags: [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [andela](<https://devfeed.tech/tags/andela.md>), [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [azure](<https://devfeed.tech/tags/azure.md>), [connect](<https://devfeed.tech/tags/connect.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [model-context-protocol-mcp](<https://devfeed.tech/tags/model-context-protocol-mcp.md>), [post-contributed](<https://devfeed.tech/tags/post-contributed.md>), [security](<https://devfeed.tech/tags/security.md>), [sponsor-andela](<https://devfeed.tech/tags/sponsor-andela.md>), [sponsored-post-contributed](<https://devfeed.tech/tags/sponsored-post-contributed.md>), [token](<https://devfeed.tech/tags/token.md>)

## AI overview

The author measures the permissions and audit visibility inherited when an AI coding agent uses a developer's Azure credentials across production and non-production data stores. The findings include inconsistent privilege scopes, gaps in audit coverage, and limited ability to distinguish agent actions from human actions. The article proposes delegated identities, permission limits, action-based scopes, privilege-linked auditing, and independent revocation, while noting that the measurements cover one estate over two days.

## Source excerpt

I measured what an AI agent actually holds when it authenticates as me. Authentication turned out to be a token The post The audit log says my name: what an agent inherits when you hand it your credentials appeared first on The New Stack.