Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:HSummary
CVE-2026-34935 is a critical-severity OS Command Injection (CWE-78) vulnerability in Praison Praisonai. Its CVSS base score is 9.8 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked in the top 46% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Supply Chain and Deployment risk domain.
The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2026-34935 is a critical command injection vulnerability (CWE-78) in PraisonAI, a multi-agent teams system. It affects versions 4.5.15 through 4.5.68, where the --mcp CLI argument is passed directly to shlex.split() and forwarded unsanitized through the call chain to anyio.open_process(), enabling arbitrary OS command execution as the process user.
Remote attackers require no privileges or user interaction to exploit this vulnerability, which has a CVSS v3.1 base score of 9.8 (AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H). By supplying a malicious --mcp argument, attackers can execute arbitrary commands on the host system with the privileges of the PraisonAI process, potentially achieving full compromise including data exfiltration, persistence, or further lateral movement.
The vulnerability has been patched in PraisonAI version 4.5.69. Mitigation details are available in the GitHub security advisory at https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9gm9-c8mq-vq7m and the patching commit at https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c.
Given PraisonAI's role as a multi-agent teams system, this flaw underscores command injection risks in AI/ML development tools that rely on CLI interfaces for process spawning.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-18913
Vulnerability Data
PraisonAI is a multi-agent teams system. From version 4.5.15 to before version 4.5.69, the --mcp CLI argument is passed directly to shlex.split() and forwarded through the call chain to anyio.open_process() with no validation, allowlist check, or sanitization at any hop,…
more
allowing arbitrary OS command execution as the process user. This issue has been patched in version 4.5.69.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Supply Chain and Deployment
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: mcp
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.2.5V1.2.8V15.2.5
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation can discover missing or incorrect command sanitization during development.
Input validation directly neutralizes or rejects special characters that would otherwise alter OS command structure.
Least privilege reduces the permissions available to any process that could be subverted by injected commands.
Least functionality restricts available OS commands and interpreters, limiting the blast radius of injection.
Secure engineering principles require proper neutralization of untrusted input before command construction.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
PR.PS-06's SDLC practices directly require secure coding and input handling that blocks command-injection defects, yet the single broad outcome leaves many specific neutralization vectors and verification gaps unaddressed.
Routine patching/maintenance can remediate known command-injection CVEs in dependencies (partial forward) but does nothing to stop developers from introducing improper neutralization in custom code (none reverse).
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing and code review target insecure use of operating-system command interfaces, catching command-injection flaws introduced during development.