Skip to main content
Mallory
← Back to News
ai-platform-securityendpoint-software-vulnerabilityinitial-access-methodwidely-deployed-product-advisory

GitSpawn Lets Malicious Git Configs Execute Code Through AI Coding Agents

Emerging Technology Risk · 6 sources · Updated 2mo ago · First seen Sep 2, 2026

GitSpawn Lets Malicious Git Configs Execute Code Through AI Coding Agents

Manifold Security disclosed GitSpawn, a vulnerability class in which AI coding agents automatically invoke Git commands such as git status or git diff while opening a repository, causing attacker-controlled core.fsmonitor commands in the repository’s .git/config to execute. The commands run with the developer’s local user privileges, outside the agent sandbox and before trust or approval controls may apply, enabling code execution without a build step or explicit user action. The technique extends a previously demonstrated abuse of Git’s legitimate FSMonitor feature, which can also trigger when IDEs such as VS Code or Cursor inspect a malicious repository.

Affected products reportedly included goose, OpenAI Codex, Claude Code, Hermes Agent, Qwen Code, Grok Build, and Cursor. Patches were available for goose, Codex, Cursor, and one Claude Code path, while Hermes Agent, Qwen Code, Grok Build, and another Claude Code issue remained unresolved or unpatched. The primary exposure is repositories delivered locally with a preserved .git directory, including ZIP archives; ordinary cloning, pulling, and fetching do not transfer the malicious local configuration. Organizations should treat locally received repositories as untrusted, audit for suspicious core.fsmonitor settings, disable FSMonitor by default where feasible, and update affected agent tools.

New surface, new adversariesTrack how attackers are adapting to this technology.
Track this risk
Event timeline

How this story unfolded

Events from the most recent confirmed update back to the earliest known activity.

11 events · Sep 1, 2026
  1. Reported Sep 3, 20263mo ago

    Hermes Agent GitSpawn flaw fixed and assigned CVE-2026-71963

    CVE-2026-71963 affects Hermes Agent versions 0.18.2 through 0.21.0, where a malicious repository can set core.fsmonitor and cause command execution when a user opens it and sends a message. The issue was fixed in commit f6234d00c5d59450adea1d7edd30ad3859375c79; exploitation could expose the user's environment, including configured provider API keys.

    CVE-2026-71963 - Hermes Agent 0.18.2 - 0.21.0 RCE via git core.fsmonitor Config Injection
  2. Reported Sep 2, 20263mo ago

    Cursor fixes related pre-trust repository command execution

    Cursor remediated a related repository-supplied setup-command issue in its CLI that could execute before the workspace-trust prompt and outside the product sandbox.

    Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
  3. Reported Sep 2, 20263mo ago

    OpenAI patches GitSpawn issues in Codex CLI and Desktop

    OpenAI fixed the affected Codex CLI releases in version 0.131.0 and released fixed Codex Desktop versions for macOS and Windows. OpenAI published three CVEs for the vulnerability class, including CVE-2026-19592, which could permit code to read, modify, or delete user files and access account-available resources.

    Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
  4. Reported Sep 2, 20263mo ago

    Goose releases fsmonitor fix and receives CVE-2026-72718

    Goose versions before 1.44.0 were affected by the repository-controlled fsmonitor execution issue, and version 1.44.0 fixed it. GitHub assigned CVE-2026-72718, with a CVSS 4.0 base score of 7.0.

    Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
  5. Reported Sep 2, 20263mo ago

    Anthropic advisory identifies fsmonitor execution in Claude Code

    Anthropic's June advisory for CVE-2026-55607 identified execution of Git fsmonitor during Claude Code worktree operations.

    Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
  6. Reported Sep 2, 20263mo ago

    Sonar reports Git execution sink in AI-agent workflows

    Sonar reported the same Git execution sink in April and noted earlier workspace-trust-dialog bypasses affecting Visual Studio Code and JetBrains IDEs. The report identified repository-triggered Git execution as a risk before the later GitSpawn disclosure.

    Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
  7. Reported Sep 2, 20263mo ago

    Hermes Agent, Qwen Code, and Grok Build remain awaiting fixes

    Manifold reported confirmed GitSpawn exposure in Hermes Agent, Qwen Code, and Grok Build, with fixes pending or unresolved. Qwen Code could execute before authentication, while Grok Build could trigger execution on the first keystroke; xAI reportedly closed the Grok report as a duplicate of an earlier informative report.

    KI-Agenten führen git-Schadcode beim Starten automatisch aus | heise online
  8. Reported Sep 2, 20263mo ago

    Anthropic fixes Claude Code core.fsmonitor path

    Anthropic fixed the core.fsmonitor GitSpawn path affecting Claude Code 2.1.193 by version 2.1.196. A separate claude ultrareview path remained unresolved in Manifold's later testing.

    KI-Agenten führen git-Schadcode beim Starten automatisch aus | heise online
  9. Reported Sep 2, 20263mo ago

    Manifold discloses GitSpawn flaws across AI coding agents

    Manifold Security disclosed eight GitSpawn flaws across seven command-line AI coding agents. Received repositories retaining a malicious .git/config could cause background Git operations such as status or diff to execute attacker-controlled commands as the developer, outside agent sandboxes and without approval.

    KI-Agenten führen git-Schadcode beim Starten automatisch aus | heise online
  10. Sep 1, 20263mo ago

    Manifold tests persistent Claude Code ultrareview exposure

    Manifold tested Claude Code version 2.1.252 and found that a separate command-execution path through claude ultrareview remained active, despite a fix for the core.fsmonitor path.

    Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
  11. Reported Dec 8, 202511mo ago

    Git FSMonitor RCE technique demonstrated against developer IDEs

    A proof of concept showed that a malicious repository can set core.fsmonitor in .git/config to an attacker-controlled script, which can execute when IDEs such as VSCode or Cursor automatically run Git commands on opening the folder. The demonstration worked on macOS and was described as adaptable to Windows and Linux; it abuses legitimate Git behavior rather than a patched vulnerability.

    Red Team Technique: Exploiting Git FSMonitor for Initial Access
Linked entities

Related entities

Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.

Open in app →
Do you run this?Follow how adversaries are adapting to this technology, and where it touches your stack today.
Track This Risk
Mallory platform

See the full picture, correlated to your attack surface.

This page covers what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which threat actors are using it right now, and what to deploy next.

Exposure mappingMap indicators from this story to your assets and identify affected systems in minutes.
Threat actor evidenceEvery observed campaign, victim, and pivot linked to actors named in this story.
Associated malwareMalware, exploits, and IOCs connected to the activity described here.
Detection signaturesYARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Scheduled alertsGet matching new stories delivered to your team as they break, not the next morning.
AI threadsAsk questions about this story and take action on the answers.