Impact
The vulnerability allows arbitrary code injection through untrusted input handling in the DataInterpreter component's write_analysis_code.py file, leading to potential remote code execution or alteration of system behavior. The flaw is categorized under CWE-707 and CWE-74, indicating improper handling and failure to neutralize external input. Attackers could exploit this by supplying crafted data that the system executes, compromising confidentiality, integrity, and availability.
Affected Systems
Foundation Agents MetaGPT versions up to 0.8.1 are affected. The vulnerability resides in the DataInterpreter module of the MetaGPT framework, and any deployment of the software in its current form remains vulnerable until a patch or update is applied.
Risk and Exploitability
The CVSS base score of 5.3 denotes moderate severity, and no EPSS score is available. The vulnerability is not listed in CISA's KEV catalog, but an exploit is publicly available, and remote exploitation is possible. Attackers can target the system over the network by injecting malicious input, so monitoring and updates are essential.
OpenCVE Enrichment