Attackers use agentic tooling to find exposed secrets in public GitHub repos

Nov 6, 2026 · Issue 14 · 2 sources, 2 articles

Microsoft Threat Intelligence has observed threat actors using an agentic AI attack framework to search public GitHub repositories for exposed secrets and abuse them. The report was published on November 6, 2026.

Who is affected and how

senior developer

If a key has landed in a public repo, treat it as compromised immediately, and do not just delete the commit.

Narrative: The coding agent is the new attack surface

Sources

• Threat actors use agentic AI tooling to find and abuse exposed secretsmicrosoft.com · Nov 6, 2026
• ARTEX: AI Agents Find and Abuse Exposed GitHub Secretsblog.gitguardian.com · Nov 6, 2026

Machine-generated summary based on the titles and excerpts of the source articles. The facts come from the linked article.