browser_evaluate

2 findings on this tool

1. criticalexcessive agencyf-r7-browser_evaluate

   Tool `browser_evaluate` exposes a code/command execution surface

   `browser_evaluate` looks like it executes code or shell commands (Evaluate JavaScript expression on page or element). 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-browser_evaluate

   Tool `browser_evaluate` accepts unconstrained string input

   The following string parameter(s) have no `maxLength` constraint: `element`, `filename`, `function`, `target`. 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