AI / ML CVE-2026-22708
CRITICALSeverity by source
AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Primary rating from GitHub Advisory · only source for this CVE.
CVSS VectorGitHub Advisory
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Lifecycle Timeline
2DescriptionGitHub Advisory
Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via indirect or direct prompt injection to poison the shell environment by setting, modifying, or removing environment variables that influence trusted commands. This vulnerability is fixed in 2.3.
AnalysisAI
Cursor AI code editor before 2.3 allows prompt injection to bypass the Agent's Allowlist mode. Shell built-ins can execute without appearing in the allowlist, enabling environment poisoning and arbitrary command execution.
Technical ContextAI
The Agent's Auto-Run Mode with Allowlist only checks explicit commands, not shell built-ins like export, alias, and set (CWE-15). Through prompt injection, an attacker can manipulate environment variables, redefine commands via aliases, and poison the shell environment.
RemediationAI
Update to Cursor 2.3 or later. Review AI agent execution logs for suspicious shell built-in usage.
MCPJam Inspector versions 1.4.2 and earlier allow unauthenticated remote code execution through missing authentication i
A path traversal vulnerability exists in mlflow/mlflow version 2.15.1. Rated high severity (CVSS 7.5), this vulnerabilit
Code injection in Langflow CSV Agent node before 1.8.0. The node hardcodes allow_dangerous_code=True, enabling arbitrary
Langflow has a third RCE vulnerability via exec_globals (EPSS 10.0%) allowing inclusion of untrusted code that executes
Sandbox escape in Enclave JavaScript sandbox before 2.11.1. Enclave is designed for safe AI agent code execution — the e
enclave-vm JavaScript sandbox (before 2.7.0) has a critical sandbox escape. When a tool invocation fails, a host-side Er
A remote code execution vulnerability in langchain-ai/langchain (CVSS 10.0). Risk factors: public PoC available. Vendor
n8n has a fifth critical RCE vulnerability (CVSS 9.9) in the Expression evaluator, enabling code execution through craft
Path traversal vulnerability in RAGFlow RAG engine version 0.23.1 allows unauthenticated attackers to read arbitrary fil
WeKnora LLM framework (before 0.2.5) allows authenticated users to inject MCP stdio commands that the server executes as
OS command injection in WeKnora from version 0.2.5 allows authenticated users to execute arbitrary system commands. CVSS
Shell command injection in Nuclio serverless framework before 1.15.20. PoC and patch available.
Same technique Code Injection
View allShare
External POC / Exploit Code
Leaving vuln.today