jailbreak-archives
A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-teaming, and defensive hardening.
This is 1 of 62 launches in adversarial security and jailbreaking tools — see how it stacks up on momentum and crowding →
1521 other launches read as similar to this one →
Details
- External ID
- 1397292246
- Source
- GITHUB
- Company
- —
- Product
- jailbreak-archives
- Website domain
- youtube.com
- Launched
- Sept. 30, 2026
- Cohort
- —
- Upvotes
- 9
- Upvotes percentile
- 0.2180896543300354
- Tags
- adversarial-prompts, ai-alignment, ai-red-team, ai-safety, chatgpt, claude, cybersecurity, deepseek, jailbreak, llm, llm-jailbreak, llm-security, machine-learning, offensive-security, prompt-engineering, prompt-injection, qwen, red-teaming, responsible-disclosure, security-research
- Fetched at
- Oct. 2, 2026, 1:02 a.m.
- Updated at
- Oct. 2, 2026, 1:02 a.m.
Enrichment
- Theme
- adversarial security and jailbreaking tools
- Vertical
- Security
- Function
- Data infrastructure
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- archive of adversarial prompt engineering techniques for ai safety research
- Manually corrected
- False
Could you build this?
Yes It is a curated markdown/database archive and simple web UI or GitHub repo documenting jailbreak prompts for LLMs.
Competitors
Other products that read as similar to this one — 1521 launches clear the similarity bar, closest 8 shown.
Attention rank: #1093 of 1522 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 336 days after the earliest competitor.
- genpark-adversarial-prompt-jailbreak-detector-skill · github · 2026-09-26 · 7 upvotes · similarity 0.67
- adeskills · github · 2026-09-27 · 69 upvotes · similarity 0.63
- Lelu · hn · 2026-06-24 · 6 upvotes · similarity 0.60
- Offensive-Security-AI-Models · github · 2026-09-27 · 511 upvotes · similarity 0.59
- ml-refusal-neurons · github · 2026-09-15 · 8 upvotes · similarity 0.59
- Open-source playground to red-team AI agents against public prompts · hn · 2026-08-09 · 13 upvotes · similarity 0.59
- VoiceGoat · hn · 2026-04-28 · 14 upvotes · similarity 0.58
- misalignment · github · 2026-09-20 · 30 upvotes · similarity 0.58
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a data infrastructure tool for Media & entertainment yet.