Secure Autonomous
FeedbackGet alertsCheck a deployment
Signals › SIG-2026-11-11-003

Microsoft report: threat actors used an agentic offensive framework to search public GitHub repositories for exposed secrets and use them, in one case reaching Azure Key Vault data in five minutes

Microsoft Threat Intelligence reports that from August 2026 threat actors used an agentic artificial intelligence (AI) offensive framework to search public GitHub repositories for exposed secrets, and that from as early as 28 October 2026 an agentic framework used leaked or stolen application credentials to sign in to organizations' Microsoft Entra ID tenants and exfiltrate credentials and data, in one observed case progressing from searching GitHub for client secrets to exfiltrating data from Azure Key Vault in five minutes.

ReportSoftware agents · Enterprise work agentsRecord published 2026-11-05Posted 2026-11-11
SIG-2026-11-11-003Company statement ↗

The record

Kind
Report
Source record
Threat actors use agentic AI tooling to find and abuse exposed secrets (Microsoft Threat Intelligence and Microsoft Security Research), 5 November 2026 (Company statement)
Record published
2026-11-05
Posted here
2026-11-11
World
Software agents · Enterprise work agents
Controls concerned
none tagged
Checked
Checked against its record on 2026-11-11 by a reader who did not draft it; report verification/reports/SIG-2026-11-11-003-2026-11-11.md.

A signal's controls are the ones its record points at, the exposure; a case's controls are the ones its records show were absent or failed, so the two can differ.

Corrections

Changes to what this signal says, with the reason. Every earlier version is kept.

What a signal is. A signal records what a primary record says; it assigns no fault. It is lighter than a case: one dated item from one record, tagged with the world, sector and controls it touches. It becomes a case when it meets the bar for one.

New signals like this, once a week. A short email when a case, signal or rule touches software agents. Free; unsubscribe in one click.

Get the weekly email

Newer: CVE-2026-102610: fast-agent's server mode lets an unauthenticated network client invoke the agent's tool, and with --shell cause operating-system commands to run; fixed in 0.7.21
Older: OpenAI misalignment report: a research model in a coding evaluation bypassed its sandbox's network restrictions and reached Amazon S3 and Microsoft's public sign-in service (sample 4 August 2026)

Is this wrong? Dispute it with the record that shows otherwise. All signals · RSS feed.

Help shape the Register

A person reads every answer; changes it leads to are logged in the methodology. To dispute a claim or reply for a named company, use Respond, dispute, or submit.

Did this page help with what you came to do?