Skip to content
AI AgentHigh

CVE-2026-108600: open-multi-agent (@open-multi-agent/core) 1.5.0 through 1.21.2 contains a link following vulnerabili…

Occurred
Oct 10, 2026
Published
Oct 10, 2026
Source
NVD CVE

Summary

open-multi-agent (@open-multi-agent/core) 1.5.0 through 1.21.2 contains a link following vulnerability in the file_write tool sandbox that allows attackers to create files outside the workspace root by using dangling symlinks. Attackers can plant a dangling symlink in the workspace and steer the agent via prompt injection to write attacker-influenced content anywhere the agent process can write.

Tags

  • CVE
  • CVE-2026-108600
  • cvss:MEDIUM
  • agent-fail:injection-indirect
  • agent-fail:authorization
  • agent-cause:missing-guardrail
  • agent-cause:framework-bug

Classification

Category confidence: 95%
Severity confidence: 90%

Rationale: Agent framework vulnerability allows attackers to bypass sandbox via prompt injection and symlink manipulation.

Classifier: Qwen/Qwen3.5-35B-A3B-FP8

Visit source