Unauthenticated command execution via MCP process launch
Published Sep 14, 2026 · Updated Sep 14, 2026
OS command injection in PraisonAI 4.6.48 allows remote attackers to execute local processes through the UI MCP connect API. The unauthenticated endpoint passes caller-controlled command and args values to StdioMCPClient, which starts the selected process before its handshake completes. Reachability requires an exposed UI host application; default UI commands bind to all interfaces, and execution inherits the UI service account's access.
Summary
What happened
OS command injection in PraisonAI 4.6.48 allows remote attackers to execute local processes through the UI MCP connect API. The unauthenticated endpoint passes caller-controlled command and args values to StdioMCPClient, which starts the selected process before its handshake completes. Reachability requires an exposed UI host application; default UI commands bind to all interfaces, and execution inherits the UI service account's access.
The record
- CVE
- CVE-2026-57124
- Published
- Sep 14, 2026
- Updated
- Sep 14, 2026
- Vendor
- PraisonAI
- Product
- PraisonAI
- Classifications
- CWE-78, CWE-306, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 14, 2026CVE publishedPublication date reported by the CVE source.
- Sep 14, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 4.6.59
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- PraisonAI UI MCP connect minimal PoCproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo