Same AI agent, different prompts: 0% vs. 62% security pass rate1 points·by xsourcesec·il y a 6 mois·1 commentsI've been testing production AI agents for vulnerabilities.Interesting finding: System prompt design matters more than the model itself.Same agent. Same task. Same attack vectors. Only difference: how the system prompt was structured.Results: → Prompt A: 0% pass rate (failed every test) → Prompt B: 62.5% pass rateNo model change. No fine-tuning. Just prompt engineering.Anyone else seeing this pattern? What's your approach to hardening AI agents?1 commentsPost comment[–]chrisjj·il y a 6 moisreplySurely this is no more than expected. Just as say a building might have some entrances secure and others not.
Interesting finding: System prompt design matters more than the model itself.
Same agent. Same task. Same attack vectors. Only difference: how the system prompt was structured.
Results: → Prompt A: 0% pass rate (failed every test) → Prompt B: 62.5% pass rate
No model change. No fine-tuning. Just prompt engineering.
Anyone else seeing this pattern? What's your approach to hardening AI agents?