Raw vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:HSummary
CVE-2026-41208 is a high-severity OS Command Injection (CWE-78) vulnerability in Paperclip Paperclipai. Its CVSS base score is 8.8 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked at the 45th 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 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-2026-41208 is a privilege escalation vulnerability in the @paperclipai/server component of Paperclip, a Node.js server and React UI that orchestrates teams of AI agents to run a business. Versions prior to 2026.416.0 are affected, where the issue stems from agents being permitted to update their own adapterConfig via the /agents/:id API endpoint. Specifically, the adapterConfig.workspaceStrategy.provisionCommand field is modifiable and subsequently executed by the server runtime during workspace provisioning, enabling OS command injection classified under CWE-78. The vulnerability 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 remote code execution potential on the server host.
An attacker requires only an Agent API key, representing low privileges within the agent runtime, to exploit this flaw. By sending a crafted request to the /agents/:id endpoint, the attacker can inject arbitrary shell commands into the provisionCommand field of their agent's configuration. When the Paperclip server processes workspace provisioning, these commands execute with the server's host privileges, breaching the trust boundary between agent configuration and server execution. This allows escalation from agent-level access to full remote code execution on the underlying host system, potentially compromising confidentiality, integrity, and availability.
The GitHub security advisory at https://github.com/paperclipai/paperclip/security/advisories/GHSA-265w-rf2w-cjh4 details the issue and confirms that @paperclipai/server version 2026.416.0 addresses the vulnerability by preventing such unauthorized configuration updates.
In the context of AI agent orchestration platforms like Paperclip, this flaw underscores risks in systems delegating execution to untrusted agent configurations, though no public evidence of real-world exploitation is noted as of the CVE publication on 2026-04-23.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-25162
Vulnerability Data
Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. Versions of @paperclipai/server prior to 2026.416.0 contain a privilege escalation vulnerability that allows an attacker with an Agent API key to…
more
execute arbitrary OS commands on the Paperclip server host. An attacker with an agent credential can escalate privileges from the agent runtime to the Paperclip server host. The vulnerability occurs because agents are allowed to update their own adapterConfig via the /agents/:id API endpoint. The configuration field adapterConfig.workspaceStrategy.provisionCommand is later executed by the server runtime. As a result, an attacker controlling an agent credential can inject arbitrary shell commands which are executed by the Paperclip server during workspace provisioning. This breaks the intended trust boundary between agent runtime configuration and server host execution, allowing a compromised or malicious agent to escalate privileges and run commands on the host system. This vulnerability allows remote code execution on the server host. @paperclipai/server version 2026.416.0 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.