LLM Security Automation Isn’t a Drop-In Scanner Yet
An LLM Security Scanning and Review is a strong assist but a weeak gate. Why a `/security-review` slash command or agent harness is not a drop-in replacement for deterministic scanners yet: nondeterminism, confabulation, latency, cost, exploitability of generated code, and findings variance—grounded in how agent loops work and what BaxBench measures.