CVE-2026-42074
Published: 02 June 2026
Summary
CVE-2026-42074 is a critical-severity Improper Access Control (CWE-284) vulnerability in Gitlawb Openclaude. Its CVSS base score is 9.3 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 41.6th percentile by exploit likelihood (below the median); 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 LLM/Generative AI Risks risk domain.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-33972
Vulnerability details
OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version 0.5.1, the dangerouslyDisableSandbox parameter is exposed as part of the BashTool input schema, meaning the LLM (an untrusted principal per the project's own…
more
threat model) can set it to true in any tool_use response. Combined with the default allowUnsandboxedCommands: true setting, a prompt-injected model can escape the sandbox for any arbitrary command, achieving full host-level code execution. This issue has been patched in version 0.5.1.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: llm
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Vulnerability allows untrusted LLM input to directly trigger unsandboxed arbitrary command execution on host.
CVEs Like This One
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Device lock enforces restricted access until re-authentication, directly reducing unauthorized use of active sessions.
Explicitly identifying and documenting actions permitted without identification or authentication enforces proper access control boundaries by defining justified exceptions.
Requiring authorization and configuration controls for mobile device connections directly enforces access control and prevents unauthorized devices from reaching organizational systems.
Provides a tamperproof, always-invoked, and verifiable mechanism to enforce access control policies.
Provides capability to review session content, directly detecting violations of access control.
Control assessments verify that access controls are implemented correctly and operating as intended, detecting improper access control before exploitation.
Certification requires independent assessment confirming access controls are implemented correctly and effective.
Restricting available functions and services reduces the attack surface and enforces proper access control boundaries.