LIVE THREATS
CRITICAL Four OpenClaw Flaws Chain Together for Full AI Agent Compromise // CRITICAL Malicious node-ipc Versions Target Cloud, AI Tool Credentials via Supply Chain Backdoor // MEDIUM Microsoft Outlines Defense-in-Depth Framework for Autonomous AI Agents // MEDIUM Rust Compiler Project Drafts Formal LLM Contribution Policy // HIGH TanStack Supply Chain Attack Compromises OpenAI Developer Devices and Signing Certificates // HIGH TeamPCP Steals 5GB of Mistral AI Source Code via Supply Chain Attack // MEDIUM Agentic AI Red Teaming Emerges as Defence Against AI-Speed Attack Chains // HIGH AI Agents Weaponised to Generate Custom Attack Tools in LatAm Campaigns // HIGH GPT-5.5 Matches Specialist Models in Vulnerability Discovery, Democratising Cyber Offence // HIGH Microsoft MDASH Agentic AI System Discovers 16 Critical Windows Vulnerabilities //
ATLAS OWASP CRITICAL Active exploitation · Immediate action required RELEVANCE ▲ 8.9

Four OpenClaw Flaws Chain Together for Full AI Agent Compromise

TL;DR CRITICAL
  • What happened: Four chained OpenClaw flaws enable sandbox escape, credential theft, privilege escalation, and backdoor persistence in AI agent runtimes.
  • Who's at risk: Any organisation running OpenClaw-based AI agents prior to version 2026.4.22 is directly exposed to full runtime compromise.
  • Act now: Upgrade OpenClaw to version 2026.4.22 immediately · Audit AI agent plugins and external inputs for signs of malicious injection · Review MCP loopback token configurations and revoke any untrusted bearer tokens
Four OpenClaw Flaws Chain Together for Full AI Agent Compromise

Overview

Cybersecurity firm Cyera has disclosed four security vulnerabilities in OpenClaw, an AI agent runtime platform, that can be chained into a full attack sequence enabling credential theft, privilege escalation, and persistent backdoor installation. Collectively named Claw Chain, the vulnerability set is particularly significant because it exploits the trust model baked into AI agent execution environments — turning the agent’s own runtime privileges against the host system.

All four CVEs were responsibly disclosed and have been patched in OpenClaw version 2026.4.22.


Technical Analysis

The four vulnerabilities span different layers of the OpenClaw stack:

  • CVE-2026-44112 (CVSS 9.6) — A TOCTOU race condition in the OpenShell managed sandbox backend. An attacker can race the check-use window to redirect filesystem writes outside the intended mount root, enabling backdoor planting and configuration tampering.

  • CVE-2026-44113 (CVSS 7.7) — A companion TOCTOU flaw allowing reads outside the sandbox mount root, exposing system files, credentials, and internal secrets.

  • CVE-2026-44115 (CVSS 8.8) — An incomplete disallowed-inputs list that allows shell expansion tokens embedded within heredoc bodies to slip past allowlist validation, executing unapproved commands at runtime.

  • CVE-2026-44118 (CVSS 7.8) — An improper access control flaw in the MCP loopback runtime. OpenClaw trusted a client-controlled flag (senderIsOwner) to determine owner-level access without validating it against the authenticated session. A non-owner client could spoof this flag to gain full control over gateway configuration, cron scheduling, and execution environment management.

The exploitation chain follows four stages:

  1. Initial code execution via malicious plugin, prompt injection, or compromised external input inside the OpenShell sandbox.
  2. Leverage CVE-2026-44113 and CVE-2026-44115 to exfiltrate credentials, secrets, and sensitive files.
  3. Exploit CVE-2026-44118 to escalate to owner-level agent runtime control.
  4. Use CVE-2026-44112 to plant backdoors and establish persistence.

Framework Mapping

FrameworkTechniqueRationale
ATLAS AML.T0051LLM Prompt InjectionInitial foothold vector via injected agent inputs
ATLAS AML.T0057LLM Data LeakageCVE-2026-44113 exposes credentials and internal artifacts
ATLAS AML.T0018Backdoor ML ModelCVE-2026-44112 enables persistent backdoor planting
ATLAS AML.T0012Valid AccountsCVE-2026-44118 exploits trusted identity flags
OWASP LLM07Insecure Plugin DesignMalicious plugin as initial entry point
OWASP LLM08Excessive AgencyAgent runtime privileges weaponised against the host
OWASP LLM06Sensitive Information DisclosureCredential and secrets exfiltration via sandbox escape

Impact Assessment

Organisations running OpenClaw-backed AI agents in production environments are at risk of complete runtime compromise. The severity is elevated by the chained nature of the flaws — each step amplifies the next, moving from limited sandbox access to persistent host-level control. Environments where agents have access to secrets stores, internal APIs, or scheduling systems face the highest exposure.


Mitigation & Recommendations

  • Patch immediately: Upgrade to OpenClaw version 2026.4.22, which issues separate owner/non-owner bearer tokens and eliminates the spoofable senderIsOwner header.
  • Audit plugin inputs: Review all registered agent plugins and external input sources for signs of injection or tampering.
  • Restrict agent privileges: Apply least-privilege principles to agent runtime environments; limit filesystem and scheduling access.
  • Monitor for anomalous agent behaviour: Set alerts on unexpected file access patterns or configuration changes initiated by agent processes.

References

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.