pg_psql

2 findings on this tool

1. criticalexcessive agencyf-r7-pg_psql

   Tool `pg_psql` exposes a code/command execution surface

   `pg_psql` looks like it executes code or shell commands (Execute SQL queries: analyze, debug, modify schema, manage data). 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
2. mediumunconstrained inputf-r1-pg_psql

   Tool `pg_psql` accepts unconstrained string input

   The following string parameter(s) have no `maxLength` constraint: `app`, `command`, `credential`, `database`, `file`. 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.

   OWASP LLM01NIST MEASURE-2.3ATLAS T0051