Cline AI Coding Agent vulnerable to prompt injection and code execution
Mindgard AI discovered that Cline AI Coding Agent is vulnerable to prompt injection attacks embedded in source code files, which could allow attackers to execute arbitrary code by analyzing malicious repositories. The vulnerability was discovered on August 24, 2025, and disclosed to the vendor on August 27, 2025.
What happened
Cline AI Coding Agent is vulnerable to prompt injection when analyzing source code files, according to a security disclosure by Mindgard AI.
The vulnerability allows attackers to slip prompt injections into source files that can break the model's ability to analyze an entire potential execution chain for safety, enabling arbitrary code execution.
Reported impact
Exploitation requires only opening a malicious source repository and asking Cline to analyze it.
Index analysis
The vulnerabilities were discovered during a brief audit of the Cline Bot AI coding agent and were discovered on August 24, 2025.
Classification
Sources and evidence
This record was researched and written by the Index, based on the following original reporting.