Raw vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:LCVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.
Summary
CVE-2026-33718 is a high-severity OS Command Injection (CWE-78) vulnerability in Openhands Openhands. Its CVSS base score is 7.6 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked in the top 21% 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-2026-33718 is a command injection vulnerability in OpenHands, software for AI-driven development. The flaw exists in the `get_git_diff()` method at `openhands/runtime/utils/git_handler.py:134`, where the `path` parameter from the `/api/conversations/{conversation_id}/git/diff` API endpoint is passed unsanitized to a shell command. This affects OpenHands starting in version 1.5.0, with version 1.5.0 fixing the issue. It is rated with a CVSS v3.1 base score of 7.6 (AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L) and maps to CWE-78.
Authenticated attackers with low privileges can exploit the vulnerability over the network with low complexity and no user interaction. By supplying a malicious `path` parameter, they can execute arbitrary commands within the agent sandbox. Although users are already permitted to instruct the agent to execute commands through normal channels, this vulnerability bypasses those mechanisms.
The OpenHands GitHub security advisory (GHSA-7h8w-hj9j-8rjw) and pull request #13051 document the patch applied in version 1.5.0. Mitigation requires updating to the fixed version. Additional guidance from references emphasizes using `shlex.quote` for proper shell argument escaping, adhering to subprocess security considerations in Python documentation, and following OWASP recommendations to prevent command injection.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-16500
Vulnerability Data
OpenHands is software for AI-driven development. Starting in version 1.5.0, a Command Injection vulnerability exists in the `get_git_diff()` method at `openhands/runtime/utils/git_handler.py:134`. The `path` parameter from the `/api/conversations/{conversation_id}/git/diff` API endpoint is passed unsanitized to a shell command, allowing authenticated attackers to…
more
execute arbitrary commands in the agent sandbox. The user is already allowed to instruct the agent to execute commands, but this bypasses the normal channels. Version 1.5.0 fixes the issue.
- 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: ai
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.