Raw vector
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XSummary
CVE-2026-24887 is a high-severity OS Command Injection (CWE-78) vulnerability in Anthropic Claude Code. Its CVSS base score is 7.7 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked at the 44th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as Enterprise AI Assistants; in the LLM/Generative AI Risks 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-2026-24887 affects Claude Code, an agentic coding tool from Anthropic, in versions prior to 2.0.72. The vulnerability stems from an error in command parsing that allows attackers to bypass the tool's confirmation prompt, enabling execution of untrusted commands via the find command. Associated with CWE-78 (OS Command Injection) and CWE-94 (Code Injection), it carries a CVSS v3.1 base score of 8.8 (AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H), indicating high severity due to network accessibility, low attack complexity, and significant impacts on confidentiality, integrity, and availability.
Exploitation requires an attacker with low privileges (PR:L) who can introduce untrusted content into a Claude Code context window, such as through manipulated inputs or shared sessions. Once injected, the malformed find command evades the confirmation mechanism, allowing arbitrary command execution on the host system without user interaction (UI:N). This could lead to full system compromise, data exfiltration, or persistent access, depending on the attacker's privileges and the environment.
The GitHub Security Advisory (GHSA-qgqw-h4xq-7w8w) confirms the issue was patched in Claude Code version 2.0.72 by fixing the command parsing logic. Security practitioners should upgrade to 2.0.72 or later and review usage of Claude Code in contexts where untrusted content might enter the tool's window, such as collaborative coding or automated pipelines.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-5159
Vulnerability Data
Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting…
more
this required the ability to add untrusted content into a Claude Code context window. This issue has been patched in version 2.0.72.
- CWE(s)
AI Security AnalysisAI
- AI Category
- Enterprise AI Assistants
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: claude
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.2.5V1.2.8V15.2.5V1.3.1
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.
Requiring documented secure development standards and tools enforces use of safe code-generation APIs and escaping.
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).
PR.DS-10 protects runtime data confidentiality/integrity but has no bearing on neutralizing externally influenced input during code generation, so neither direction shows any preventive effect.
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.
Banning unapproved code samples and unauthenticated web services, combined with secure-coding standards and SAST, prevents the dynamic generation or inclusion of attacker-supplied code.
Controls that restrict unauthorized or malicious code from being introduced via external networks or removable media limit opportunities for an attacker to inject and execute arbitrary code.