HN Explorer

xsourcesec

↗ HN profile [ 20.4 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. 1 points 0
  3. Same AI agent, different prompts: 0% vs. 62% security pass rate

    I'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…

    1 points 1
  4. Show HN: BreachLab – Can you hack our AI? (breachlab.xsourcesec.com)

    10 AI characters guard secret codes. Your job: extract them using prompt injection. Level 1-3: Most pass Level 7-9: Security pros struggle Level 10: Still uncracked Free, no signup. Curious what techniques HN tries.

    4 points 0
  5. Show HN: GitHub Action for AI/LLM Security Scanning in CI/CD (github.com)
    5 points 1
  6. Show HN: AI Security Baseline 1.0 for LLM Apps (xsourcesec.com)
    1 points 1