Return to Threats

Critical Paperclip Flaw Allowed Admin Access, Code Execution

securityweek.com 2026-08-06 AI agent abuse Critical

Executive Summary

A critical Paperclip flaw let an attacker self-register, sign in for board-level API access and import a new company for code execution.

What Happened

An attacker could self-register, sign in for board-level API access, and import a new company for code execution. The post Critical Paperclip Flaw Allowed Admin Access, Code Execution appeared first on SecurityWeek .

Affected Products

  • Paperclip

Vulnerability / Attack Technique

Self-registration to privileged API access and code execution

Technical Mechanism

Open registration granted board-level API access, and importing a company triggered code execution.

AI Security Category

LLM03:2025 Supply Chain

Part of the AI Supply Chain and AI SBOM topic.

Relevant Frameworks

LLM03:2025 Supply ChainMITRE ATLAS: Execution

RealGround Analysis

Paperclip is a control plane for AI agent teams, so its compromise controls the agents. RealGround analysis: agent control planes need closed registration and strict API authorization.

Recommended Controls

  • Update Paperclip
  • Disable open registration
  • Restrict board-level API access

Related RealGround Service

AI Agent Business Logic Audit · or start with the free AI Agent Security Scanner.

Sources

securityweek.com: https://www.securityweek.com/critical-paperclip-flaw-allowed-admin-access-code-execution/

Summary and analysis written by RealGround from the source above; last updated 2026-10-18.

Talk to AI CISO