Vulnerabilities & Exploits

Imported Agents Become Server Commands in Paperclip

Paperclip breaks the normal boundary between configuration and execution. A user who should only be able to import an agent can end up making the server run host commands, and the local_trusted mode flaw lets the same thing reach developer machines through a browser.

Oasis Security found CVE-2026-41679 in authenticated deployments and a second critical path in local_trusted mode. The first flaw turns self-registration into a persistent board-level API key, then uses that key to reach an import route that trusts board-level access too much; the second lets a browser-originated request import and wake a malicious agent on the host. A third access-control flaw exposed control-plane data, and Rapid7 has already released a Metasploit module for CVE-2026-41679.

The practical risk is wider than one product bug. Any AI agent control plane that treats imported workflows or agents as safe input can hand execution to lower-privilege users, and patching only closes the entry point, not the need to review what registration and import trust in the first place.

3 sources · Aug 6

CVE-2026-41679

NVD KEV

CVSS 10 CRITICAL: paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. EPSS 7% (94th percentile).

Timeline

Aug 6 Reported by SecurityWeek
Aug 5 Reported by The Hacker News

Sources

Aug 6 SecurityWeek
Critical Paperclip Flaw Allowed Admin Access, Code Execution
An attacker could self-register, sign in for board-level API access, and import a new company for code execution.
original
Aug 5 The Hacker News
Paperclip AI Flaws Let Attackers Run Host Commands via Malicious Agent Imports
Paperclip flaws could let attackers run commands on servers or developer machines; v2026.416.0 adds import checks and hostname validation.
original
Aug 5 Infosecurity Magazine
Paperclip AI Flaws Let Unauthenticated Attackers Run Commands
3 Paperclip flaws exposed data & allowed unauthenticated command execution in two deployment modes
original

Part of the PlainSec briefing for 2026-08-07

Every edition of this story: Imported Agents Become Server Commands in Paperclip

More from today

Vulnerabilities & ExploitsImported Agents Become Server Commands in PaperclipPaperclip breaks the normal boundary between configuration and execution. A user who should only be able to import an agent can end up making the server run host commands, and the local_trusted mode flaw lets the same thing reach developer machines through a browser.Oasis Security found CVE-2026-41679 in authenticated deployments and a second critical path in local_trusted mode. The first flaw turns self-registration into a persistent board-level API key, then uses that key to reach an import route that trusts board-level access too much; the second lets a browser-originated request import and wake a malicious agent on the host. A third access-control flaw exposed control-plane data, and Rapid7 has already released a Metasploit module for CVE-2026-41679.The practical risk is wider than one product bug. Any AI agent control plane that treats imported workflows or agents as safe input can hand execution to lower-privilege users, and patching only closes the entry point, not the need to review what registration and import trust in the first place.3 sources · Aug 6

CVE-2026-41679

NVD KEV

CVSS 10 CRITICAL: paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. EPSS 7% (94th percentile).

Timeline

Aug 6 Reported by SecurityWeek

Aug 5 Reported by The Hacker News

Sources

Aug 6 SecurityWeek

Critical Paperclip Flaw Allowed Admin Access, Code Execution

An attacker could self-register, sign in for board-level API access, and import a new company for code execution.

original

Aug 5 The Hacker News

Paperclip AI Flaws Let Attackers Run Host Commands via Malicious Agent Imports

Paperclip flaws could let attackers run commands on servers or developer machines; v2026.416.0 adds import checks and hostname validation.

original

Aug 5 Infosecurity Magazine

Paperclip AI Flaws Let Unauthenticated Attackers Run Commands

3 Paperclip flaws exposed data & allowed unauthenticated command execution in two deployment modes

original

Part of the PlainSec briefing for 2026-08-07Every edition of this story: Imported Agents Become Server Commands in PaperclipMore from today

Cisco IOS XE Fixes Expose Broader Codebase Weaknesses

Container Escape Turns Old Linux Bug into Host Risk

Elementor Pro Upload Check Opens PHP Write Path