CVE-2026-31236
CriticalCVSS 9.8Exploitation Probability (EPSS)
Low risk25th percentile - higher than 25% of all known CVEs
Summary
The llm CLI tool through version 0.27.1 contains a critical code injection vulnerability via the --functions argument. This argument allows custom Python function definitions, but the code is directly executed using the unsafe exec() function without any sanitization. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code and tricking a victim into running it.
Risk Assessment
The risk for the organization includes full system compromise by the attacker, potentially leading to data theft, malware installation, or further attacks on the infrastructure.
Recommendation
Immediately update the llm tool to the latest version that fixes this vulnerability. Until updated, avoid using the --functions argument with untrusted data.
Original NVD description (English source)
The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control.