Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:HSummary
CVE-2025-54382 is a critical-severity OS Command Injection (CWE-78) vulnerability in Cherry-Ai Cherry Studio. Its CVSS base score is 9.6 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked in the top 8% 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 Protocol-Specific 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.
Cherry Studio, a desktop client supporting multiple LLM providers, contains a remote code execution vulnerability in version 1.5.1 when connecting to streamableHttp MCP servers. The flaw stems from implicit trust in OAuth authentication redirection endpoints combined with insufficient URL sanitization, classified under CWE-78 as an instance of OS command injection. The vulnerability carries a CVSS 3.1 score of 9.6 reflecting network attack vector, low complexity, no required privileges, and required user interaction that leads to high impact on confidentiality, integrity, and availability with changed scope.
An attacker can exploit the issue by supplying a malicious streamableHttp MCP server URL that triggers unsanitized OAuth redirection handling, resulting in arbitrary code execution on the victim desktop client. Successful exploitation grants the attacker full control over the affected system without needing prior authentication on the target.
The referenced GitHub Security Advisory states that the issue has been resolved in version 1.5.2, indicating that updating to the patched release is the primary mitigation step.
EPSS remains at a modest 0.0238 with no material increase from its recorded peak, providing no indication of emerging exploitation interest after disclosure.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-24569
Vulnerability Data
Cherry Studio is a desktop client that supports for multiple LLM providers. In version 1.5.1, a remote code execution (RCE) vulnerability exists in the Cherry Studio platform when connecting to streamableHttp MCP servers. The issue arises from the server’s implicit…
more
trust in the oauth auth redirection endpoints and failure to properly sanitize the URL. This issue has been patched in version 1.5.2.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Protocol-Specific Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: llm, 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.