QWED-AI vulnerabilities
We track 2 vulnerabilities in QWED-AI products across 2 products. 2 are rated high or critical, and none are known to be exploited. The most recent was published on August 25, 2026.
2vulnerabilities
1critical
1high
0exploited
9.3average CVSS score
Latest QWED-AI vulnerabilities
- 8.8 High severity
qwed-verification: Improper Control of Generation of Code
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 Sym
- 9.8 Critical severity
qwed-mcp: Improper Control of Generation of Code
QWED-MCP is a deterministic verification gateway for MCP. Prior to 0.2.1, verify_math_expression() in src/qwed_mcp/engines/math_engine.py passes attacker-controlled expression and claimed_result strings directly to SymPy's parse_expr() after only normalizing c