AG-017
Destructive Operations Without Approval
critical
Page text and source link for your AI assistant. Nothing is sent automatically.
What Foo Guard detects
The agent can modify resources while destructive operation approval is explicitly disabled.
When this rule triggers
destructiveOperationsRequireApproval is false and a tool can modify resources.
Foo Guard evaluates the normalized configuration supplied to the scanner. A finding describes configuration risk; it does not establish that an attack occurred. An absent finding does not prove that an undeclared capability is safe.
How to fix
Require approval for destructive operations and enforce it in the execution path. Test a denied operation, not only the happy path.
Verify the change
Update the actual agent configuration and the underlying permissions or controls, then run the scanner again. Inspect the finding’s evidence path to confirm the intended setting changed. Do not clear a finding by changing a declaration that no longer reflects the deployed agent.