HighVulnerabilityLLM-specific
CVE-2026-10214: zhayujie chatgpt-on-wechat OS command injection in Bash Tool
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-10214
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 1.5%
Summary
A weakness in zhayujie chatgpt-on-wechat up to 2.0.8 lets a remote attacker run OS command injection through the _get_safety_warning function in agent/tools/bash/bash.py, part of the Bash Tool component. A public exploit is available and could be used in attacks.
Mitigation
Upgrade to version 2.0.9, which the source says addresses the issue. The patch is identified as 16d9b449c9aa53ccee44144a762a2737d7ba4fc4.
Related items
- HighGHSA-64vx-6h2c-rjh7: Banks: Unsafe importlib.import_module of attacker-controlled Tool.import_path in CompletionExtension allows RCESimilar attack · GitHub Advisory Database
- MediumHacking on Autopilot: Inside ARTEX Cybercrime CampaignsSimilar attack · Check Point Research
- MediumCVE-2026-122160: myshell-ai AIlice HuggingFace Model Wrapper untrusted model loadingSimilar attack · NVD/CVE Database
- MediumCVE-2026-122159: Edge0-AI Audio8_TTS path traversal via slow_decode_models argumentSimilar attack · NVD/CVE Database
- MediumCVE-2026-122235: Jan workspace guard bypass allows file writes outside workspace via symlinksSimilar attack · NVD/CVE Database