CyberRota Analysis
AI-GeneratedThe QWED open-source AI verification infrastructure is vulnerable due to improper handling of caller-controlled math expressions, allowing attackers to execute arbitrary Python code via the API server. This flaw can lead to severe impacts, including unauthorized file access, data modification, and service disruption, particularly in shared deployments. Organizations using versions prior to 5.1.2 should prioritize patching this vulnerability to mitigate potential exploitation risks.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
QWED is open-source AI verification infrastructure for deterministic verification of LLM outputs, tool calls, code, schemas, and agent state before production execution. Prior to 5.1.2, the qwed package passes caller-controlled math expressions directly to SymPy parse_expr() without restricted global_dict and local_dict namespaces, allowing Python eval() to resolve builtins and execute arbitrary Python code in the API server process. In src/qwed_new/api/main.py, POST /verify/math is protected by get_current_tenant but accepts any valid tenant API key, reads the expression field, applies only a cosmetic re.sub(r'(\d)(()', r'\1*\2', expression) normalization, and passes the result to parse_expr(). In src/qwed_new/core/batch.py, POST /verify/batch sends math items through batch_service.create_job(), stores item.query verbatim, and _verify_item() passes VerificationType.MATH input to parse_expr() without sanitization. The default-enabled POST /auth/signup endpoint allows anyone to create a standard tenant account, POST /auth/api-keys issues an x-api-key, and either vulnerable path can then be used to read or write files, modify data, execute operating system commands, terminate the service, and compromise other tenants in a shared deployment. This issue is fixed in version 5.1.2.