🧨
Anti-Patterns: Safety
Safety mechanisms that backfire — reactive guardrail stacking that creates chaos, and architectural blindness to prompt injection.
2 patterns
Guardrail Whack-a-Mole
🚫Intermediate
Reactively stacking guardrails and filters to block each new failure, creating a brittle patchwork that’s expensive to maintain and easy to circumvent.
Prompt Injection Blindness
🚫Advanced
Failing to defend against prompt injection at the architectural level — treating it as an edge case rather than a fundamental threat model.