⚠ Reference material — not professional advice. Test in staging, back up first, verify against your specific version. Use your own judgment for your environment.
● Critical · CVSS 9.8

How to Fix CVE-2026-0761: Code Injection RCE in MetaGPT

Other vulnerabilities in the same area that are worth patching alongside this one:

*By Sai Kiran Pandrala*

⚡ At a glance
SeverityCVSS 9.8 - Critical
Actively exploited?Not currently listed in CISA KEV
Affected0.8.1
Fixed inSee vendor advisory
Type (CWE)CWE-94: Improper Control of Generation of Code ('Code Injection')

What is CVE-2026-0761?

CVE-2026-0761 is a code injection flaw in MetaGPT. Attacker-controlled input is evaluated as code by the application runtime, giving the attacker arbitrary execution inside the process. Vendor description: Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Foundation Agents MetaGPT.

Why this CVE matters

Code injection against an application server is a direct path to remote code execution. The attacker executes inside the application runtime, which means database credentials, integration keys, and any secrets the process has loaded in memory are all exposed.

For deployments of MetaGPT that have been exposed to the public internet during the disclosure window, the operating assumption should be that scanning has already happened. Even where exploitation has not been publicly observed, scanning for the vulnerable fingerprint is cheap and routine. Patching closes the door; log review and credential rotation close out the rest of the response.

Am I affected?

You are affected if your installation matches any of these version ranges:

Check your installed version against the list above. If you cannot determine the version, treat the system as affected and follow the upgrade path below.

Open MetaGPT's About dialog or run the vendor-documented version-check command. Compare the result against the affected ranges in the advisory.

How to fix CVE-2026-0761

The fix is to apply the patched build listed in the Foundation Agents advisory.

Affected versions confirmed in the CVE record:

Patch via the OS package manager (Linux)


<!-- enrich_agent_2:v1 -->
# 1. Update the package metadata.
sudo apt update                                  # Debian / Ubuntu
sudo dnf check-update                            # RHEL / Rocky / AlmaLinux / Fedora
sudo zypper refresh                              # openSUSE

# 2. Pull the patched version listed in the [vendor advisory](https://www.zerodayinitiative.com/advisories/ZDI-26-027/) of MetaGPT from Foundation Agents.
sudo apt install --only-upgrade metagpt
sudo dnf upgrade metagpt
sudo zypper update metagpt

# 3. Restart the affected service so the patched binary is the running binary.
sudo systemctl restart metagpt || true

# 4. Verify the running version.
metagpt --version

Verify the fix worked


<!-- enrich_agent_2:v1 -->
# 1. Confirm the running version matches the fixed-in version from the advisory.
#    Cross-check against the vendor advisory: https://www.zerodayinitiative.com/advisories/ZDI-26-027/

# 2. Re-scan with your vulnerability scanner. The scanner should no longer flag
#    this CVE on the patched host.
# Example with Nmap NSE:
nmap -sV --script vuln <target-host>

# 3. Inspect the service / kernel logs for crash-loops or rollback events in
#    the first hour after the upgrade.
journalctl -u <service-name> --since "1 hour ago"
dmesg --since "1 hour ago"

If you cannot patch immediately

No official workaround exists beyond restricting network exposure to the affected component. Apply the vendor patch as the primary remediation.

How to verify the fix worked

If your installation was internet-reachable during the disclosure window, treat log review as part of the remediation rather than an optional follow-up. Look for unexpected administrator accounts in MetaGPT, scheduled tasks or cron jobs you did not create, new files in web-accessible directories, and outbound connections to addresses not in your baseline. Suspicious requests to the vulnerable endpoint immediately followed by successful 200-class responses with unusually large bodies are a strong indicator of exploitation.

Frequently asked questions

Is CVE-2026-0761 being exploited in the wild?

Public exploitation has not been confirmed by CISA at the time of writing. Treat the patch as time-sensitive anyway; reports often lag actual abuse.

Will a WAF or IDS rule fully mitigate CVE-2026-0761?

No. Network-layer filters can reduce noise and slow opportunistic scanners, but they will not stop a determined attacker. The vendor patch is the only durable fix.

Do I need to assume compromise if my MetaGPT was internet-facing and unpatched?

For an unauthenticated RCE-class flaw exposed to the public internet during the known exploitation window, yes. Review logs, rotate credentials the process could access, and look for unexpected accounts, scheduled tasks, or outbound connections.

References

*This guide was assembled from the official vendor advisory, the NVD record, and the CISA KEV catalog entry on 2026-05-25. Always confirm against the vendor advisory before applying changes in production.*