LLMHigh
CVE-2026-117569: Kali-GPT through commit a608c74 contains an OS command injection vulnerability in execute_tool() in …
- Occurred
- Oct 27, 2026
- Published
- Oct 27, 2026
- Source
- NVD CVE
Summary
Kali-GPT through commit a608c74 contains an OS command injection vulnerability in execute_tool() in kali_gpt/tools/mcp_server.py that allows MCP clients to run commands via unsanitized scanner parameters. Attackers or prompt-injected agents can embed shell metacharacters in parameters like target, ports, domain, wordlist, or url, executed via subprocess.run with shell=True as the MCP server user.
Tags
- CVE
- CVE-2026-117569
- cvss:HIGH
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: OS command injection vulnerability in LLM tool execution allows attackers to run arbitrary commands via prompt injection.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8