CVE-2026-59726: CVE-2026-59726: Ruflo is an agent meta-harness for Claude Code and Codex. Prior to 3.16.3, ruflo's default…

CVE-2026-59726 at a glance

CVE-2026-59726 is a critical-severity OS Command Injection vulnerability in Ruflo, with a CVSS 3.1 base score of 10. NVD published it on 2026-07-09 and classifies the weakness as CWE-78, CWE-306 and CWE-942. Public exploit code: 1 Exploit-DB entry, with the earliest exploit evidence dated 2026-11-11. FIRST EPSS puts the probability of exploitation activity in the next 30 days at 6.24% (percentile 93.6, scored 2026-11-14). NVD does not list a fixed version, so the vendor advisory is the reference for the fix. CVERadar maps 3 MITRE ATT&CK techniques across Initial Access, Execution, Stealth, Persistence and Privilege Escalation, inferred from the CWE and the description. Its CVERadar threat level is 59/100.

What it is

Ruflo is an agent meta-harness for Claude Code and Codex. Prior to 3.16.3, ruflo's default docker-compose deployment exposed the MCP bridge POST /mcp and POST /mcp/:group endpoints without authentication, allowing an unauthenticated network attacker to invoke tools/call to terminal_execute, obtain a shell in the bridge container, read provider API keys, and poison AgentDB learning-store patterns. This issue is fixed in version 3.16.3.

Exploitation evidence

First exploit evidence seen: 2026-11-11 (earliest date across the sources below).

Exploited in the wild

No source on this site lists in-the-wild exploitation yet (CISA KEV, VulnCheck KEV).

Public exploit code

Exploit-DB

• Exploit-DB EDB-52705: Ruflo MCP Bridge 3.16.2 - Remote Code Execution (2026-11-11)

GitHub proof-of-concept repositories below quality bar

1 public repositories from 1 accounts, first seen 2026-07-30.

Verify before running: public PoCs can be malicious. Read the code and only run it in an isolated lab. A PoC means exploit code is public, not that this CVE is exploited in the wild.

Sources: Exploit-DB (OffSec) · nomi-sec/PoC-in-GitHub.

Patches, mitigations and detection

Fixed versions

NVD does not list a fixed version for this CVE. Use the vendor advisory below.

Derived from the NVD CPE configuration (versionEndExcluding / versionEndIncluding). Always confirm with the vendor advisory.

Vendor advisories and patches

No vendor-tagged reference yet; see the full reference list.

MITRE ATT&CK mitigations for this chain

• M1048 Application Isolation and Sandboxing (for T1190) : Application isolation will limit what other processes and system features the exploited target can access.
• M1037 Filter Network Traffic (for T1190) : Restrict outbound network traffic from public-facing servers to prevent unauthorized connections from initiating communications with attacker-controlled infrastructure. While this may not prevent the initial exploitation, it limits the attacker's ability to verify and control the compromised server post-exploit, reduci
• M1030 Network Segmentation (for T1190) : Segment externally facing servers and services from the rest of the network with a DMZ or on separate hosting infrastructure.
• M1016 Vulnerability Scanning (for T1190) : Regularly scan externally facing systems for vulnerabilities and establish procedures to rapidly patch systems when critical vulnerabilities are discovered through scanning and through public disclosure.
• M1026 Privileged Account Management (for T1190, T1078, T1059) : Use least privilege for service accounts will limit what permissions the exploited process gets on the rest of the system.
• M1050 Exploit Protection (for T1190) : Web Application Firewalls may be used to limit exposure of applications to prevent exploit traffic from reaching the application.
• M1035 Limit Access to Resource Over Network (for T1190) : Ensure that all publicly exposed services are actually intended to be so, and restrict access to any that should only be available internally.
• M1051 Update Software (for T1190) : Update software regularly by employing patch management for externally exposed applications.
• M1027 Password Policies (for T1078) : Applications and appliances that utilize default username and password should be changed immediately after the installation, and before deployment to a production environment. When possible, applications that use SSH keys should be updated periodically and properly secured. Policies should minimize (if not eliminate)
• M1018 User Account Management (for T1078) : Regularly audit user accounts for activity and deactivate or remove any that are no longer needed.

Detection Generic guidance

• Initial Access: Alert on unusual requests to the affected service (odd paths, oversized payloads, exploit strings) in WAF, reverse-proxy and application logs.
• Persistence: Look for new files in web roots, new scheduled tasks/services, and new accounts created after the exposure window.
• Privilege Escalation: Alert on processes gaining SYSTEM/root unexpectedly, and on exploitation crashes of privileged services.
• Execution: Watch for the service process spawning shells or script interpreters (cmd.exe, powershell, sh, bash, python) via EDR process-tree rules.

Response checklist Generic guidance

1. Inventory: find every instance of the affected product and version (include internet-facing and forgotten ones).
2. Patch or mitigate per the vendor advisory; if you cannot patch, remove internet exposure or apply the vendor workaround.
3. Assume compromise if the system was exposed before patching: hunt for the indicators in the advisory and review logs back to the disclosure date.
4. Rotate credentials and secrets stored on or used by the affected system if compromise cannot be ruled out.