mcp-server-sqlite
pypi:mcp-server-sqlite@2025.4.25
Severity breakdown
Worst finding
Tool `read_query` exposes a code/command execution surface
· read_query
`read_query` looks like it executes code or shell commands (Execute a SELECT query on the SQLite database). 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.
All 9 findings
- criticalTool `read_query` exposes a code/command execution surface· read_queryexcessive agency
`read_query` looks like it executes code or shell commands (Execute a SELECT query on the SQLite database). 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.
- criticalTool `write_query` exposes a code/command execution surface· write_queryexcessive agency
`write_query` looks like it executes code or shell commands (Execute an INSERT, UPDATE, or DELETE query on the SQLite database). 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.
- highTool `write_query` name implies a side effect that is not declared· write_queryexcessive agency
`write_query` looks like a side-effecting tool (its name contains a mutation verb), but its `side_effects` declaration is []. A policy synthesizer cannot produce safe rules for this tool because it cannot tell what it actually does.
fix: Declare the tool's true side effects explicitly. If the tool is genuinely read-only, rename it to match (e.g. `email.preview` rather than `email.send`).
- highTool `create_table` name implies a side effect that is not declared· create_tableexcessive agency
`create_table` looks like a side-effecting tool (its name contains a mutation verb), but its `side_effects` declaration is []. A policy synthesizer cannot produce safe rules for this tool because it cannot tell what it actually does.
fix: Declare the tool's true side effects explicitly. If the tool is genuinely read-only, rename it to match (e.g. `email.preview` rather than `email.send`).
- mediumTool `read_query` accepts unconstrained string input· read_queryunconstrained input
The following string parameter(s) have no `maxLength` constraint: `query`. Unbounded strings let an attacker stuff arbitrary payloads through the tool, including indirect-injection content.
fix: Add a `maxLength` to each string property, or constrain with an `enum` or `pattern`. Most legitimate tool inputs fit under a few hundred bytes.
- mediumTool `write_query` accepts unconstrained string input· write_queryunconstrained input
The following string parameter(s) have no `maxLength` constraint: `query`. Unbounded strings let an attacker stuff arbitrary payloads through the tool, including indirect-injection content.
fix: Add a `maxLength` to each string property, or constrain with an `enum` or `pattern`. Most legitimate tool inputs fit under a few hundred bytes.
- mediumTool `create_table` accepts unconstrained string input· create_tableunconstrained input
The following string parameter(s) have no `maxLength` constraint: `query`. Unbounded strings let an attacker stuff arbitrary payloads through the tool, including indirect-injection content.
fix: Add a `maxLength` to each string property, or constrain with an `enum` or `pattern`. Most legitimate tool inputs fit under a few hundred bytes.
- mediumTool `describe_table` accepts unconstrained string input· describe_tableunconstrained input
The following string parameter(s) have no `maxLength` constraint: `table_name`. Unbounded strings let an attacker stuff arbitrary payloads through the tool, including indirect-injection content.
fix: Add a `maxLength` to each string property, or constrain with an `enum` or `pattern`. Most legitimate tool inputs fit under a few hundred bytes.
- mediumTool `append_insight` accepts unconstrained string input· append_insightunconstrained input
The following string parameter(s) have no `maxLength` constraint: `insight`. Unbounded strings let an attacker stuff arbitrary payloads through the tool, including indirect-injection content.
fix: Add a `maxLength` to each string property, or constrain with an `enum` or `pattern`. Most legitimate tool inputs fit under a few hundred bytes.
How this was scored
Source sandbox — live tools/list captured in an ephemeral Docker container (parameter schemas included → R1/R2/R4 fire). Findings are emitted by the public capframe.findings.v1 schema. Score = 100 − (10·Critical + 4·High + 2·Medium + 1·Low), clamped to [0, 100].
Disagree with a finding? Open an issue.