Invariant Labs demonstrated that a malicious issue in a public repository could lead an agent using the GitHub MCP server to read the user's private repositories and publish the data in a public pull request. The firm tested with Claude 4 Opus and argues there is no server-side patch because the flaw lies in agent permissions, recommending per-session repository scoping and runtime monitoring.
Why it matters
It is a canonical 'toxic agent flow' where legitimate tools and a broad token combine into a data leak.
Key facts
As stated in the sources, with where to find them.
- The attack was demonstrated with Claude 4 Opus.Main write-up
- Invariant states the issue is architectural and cannot be fixed by a GitHub server-side patch alone.Mitigations
Findings that cite this record
Key questions this bears on
- Where are deployed AI agents actually being exploited?Exploitation often reaches deployed agents through connectors, credentials, tools and packages.
Sources
Related records
Apr 1, 2025
Jul 8, 2025
Aug 6, 2025
Jun 10, 2025
Oct 29, 2026
Oct 8, 2025