immu4989/dspy-security-bench

Open, privacy-bounded assurance for AI agents: containment provenance, identity passports, authorization twins, OTel evidence, CI gates, and OSCAL.

1 best points · 0 comments · 1 Hacker News post · 7 GitHub stars · View on GitHub

Hacker News discussions

• Does DSPy prompt optimization weaken adversarial robustness? (1 points, 0 comments, by immu4989, 2026-06-29)