Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
A security weakness in the affected technology is being tracked as a newly reported vulnerability. The command executes as the user, outside the agent's sandbox and without an approval prompt, and exploitation requires the repository to arrive.
What happened
git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code. Manifold Security has disclosed eight security flaws across seven command-line AI coding agents in which a repository's own Git configuration names a command that the agent runs on the developer's machine, four of them still unpatched at publication. A security weakness in the affected technology is being tracked as a newly reported vulnerability.
The important point is that running an affected version of the affected technology creates exposure, while an actual compromise still depends on whether the attacker can reach the trigger conditions described above.
Editorial note: this News Brief follows the available evidence and adds length only when additional facts or useful context are available. Where public reporting does not establish a specific victim sequence, CyberDeltaForce does not present one as fact.
What the reporting and advisory establish
Manifold Security has disclosed eight security flaws across seven command-line AI coding agents in which a repository's own Git configuration names a command that the agent runs on the developer's machine, four of them still unpatched at publication.
git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
A security weakness in the affected technology is being tracked as a newly reported vulnerability. The command executes as the user, outside the agent's sandbox and without an approval prompt, and exploitation requires the repository to arrive. There is no reported exploitation in the current available reporting, so the public picture at this point is a disclosed vulnerability with known exploitation conditions rather than a confirmed compromise of every affected installation. The important point is that running an affected version of the affected technology creates exposure, while an actual compromise still depends on whether the attacker can reach the trigger conditions described above. Manifold Security has disclosed eight security flaws across seven command-line AI coding agents in which a repository's own Git configuration names a command that the agent runs on the developer's machine, four of them still unpatched at publication. This is primarily a vulnerability-management story.
What this means for your environment
Move from the published facts to the technical path, exposure conditions and defensive decisions that matter in a real environment.
Attack & Exploitation Path
The sequence below shows how the vulnerability can be reached and what successful exploitation can produce. Each stage is labeled by evidence status.
Required condition: the affected technology is present and the vulnerable function is reachable in the way the software is normally used.
Required condition: attacker-controlled input or the relevant workflow reaches the affected code path.
Not publicly disclosed in enough technical detail to describe the mechanism without inference.
Not publicly disclosed in enough detail to state a specific post-exploitation result without inference.
Map the affected technology to real assets, verify the vendor fix or mitigation, confirm the vulnerable path is no longer reachable, and review relevant telemetry for behavior consistent with exploitation.
Why this matters to you
This matters because the practical risk is not the score alone — it is whether the affected technology or service exists in your environment and whether the reported trigger or exposure path can reach it. No exploitation flag is currently present in the CDF data, but that does not remove the need to validate affected systems.
Does this deserve attention in my environment?
Check the conditions below against your use of the affected technology or service.
Select the conditions that are true in your environment. Leaving a condition unselected does not mean you are safe — it only means you have not marked it as applicable.
- Search endpoint, software and asset inventory for the affected technology or service.
- Confirm the vendor-recommended fixed version or mitigation and verify deployment, not just assignment, across affected assets.
- Review relevant endpoint, application, network or identity telemetry for activity associated with exploitation of the affected component.
- Track vendor and government guidance for any change in exploitation status while remediation is underway.
What remains unconfirmed
- Available reporting does not currently indicate exploitation, but that can change as vendor, government or threat-intelligence reporting develops.
Sources & References
Original reporting and technical references are kept here for readers who want to verify the facts. Publisher names stay out of the reading flow above.