execute_scalar
on pypi:mcp-server-mssql@0.1.0
Severity
1 finding on this tool
- criticalexcessive agencyf-r7-execute_scalar
Tool `execute_scalar` exposes a code/command execution surface
`execute_scalar` looks like it executes code or shell commands (Execute SQL and return single value). Arbitrary execution is the maximal authority a tool can hold -- it subsumes every other caveat, so it should never be exposed to an agent without a hard sandbox and an explicit, narrowly-scoped capability.
fix: Do not expose raw code/shell execution to an agent. If unavoidable, run it in a disposable sandbox with no network + no host FS, gate it behind a capframe-bind capability scoped to an allow-list of commands, and require holder-of-key proof per call.
OWASP LLM08NIST MANAGE-2.2ATLAS T0051
About this tool
execute_scalar is one of 21 tools exposed by mcp-server-mssql. The server scored 68/100 overall against the capframe rule engine (source: registry). Last scanned 2026-06-05.
The findings above are emitted by the public capframe.findings.v1 schema. Disagree with one? Open an issue.