Show HN: Open-source playground to red-team AI agents against public prompts
zachdotai
13 points
4 comments
August 09, 2026
Related Discussions
Found 5 related stories in 66.2ms across 4,128 title embeddings via pgvector HNSW
- Show HN: Benchmark your eng team's AI agent maturity in 5 minutes adamgold7 · 13 pts · July 14, 2026 · 71% similar
- Show HN: I built a web tool to see and edit what an AI thinks before it answers ada1981 · 25 pts · July 09, 2026 · 66% similar
- Show HN: A replayable A2A jury for tracing how agents influence decisions nmaroulis21 · 18 pts · August 09, 2026 · 65% similar
- Show HN: Open Bot – an open-source Grok Bot that works with any agent harness mikeryan52 · 12 pts · August 19, 2026 · 62% similar
- Show HN: A verification browser for AI agents – 13ms windows, one-call checks hongnoul_ · 11 pts · July 29, 2026 · 62% similar
Discussion Highlights (3 comments)
yousefh409
Why would any company leave the enforcement of rules to an agent? If something is truly a rule, there should be code that deterministically enforces it.
mmvaid
Interesting. Is there any way companies or individuals can submit an agent before they release it and use this as a way to pentest their agent?
nourzahzah
Does Nyx solve these before you publish them? Curious whether humans are still finding breaks your own agent misses, or just the same ones slower.