Capability Thresholds and Sanitisation Blind Spots in LLM-Assisted Vulnerability Detection: A Factorial Prompt Study on a Reconstructed PHP Benchmark
Prompt engineering is widely assumed to improve large language model (LLM) performance on code security tasks, yet the conditions under which it can do so remain uncharacterised. We evaluate a fully crossed $5\times 2$ prompt factorial, five structural variants with and without category naming, on a reconstructed 360-s...