Nicholas-Kloster/claude-4.6-jailbreak-vulnerability-disclosure-unredacted

Three Claude production tiers generated functional exploit code against live infrastructure when memory-stored interaction protocols suppressed constitutional safety checks. Six submissions over 27 days. Zero acknowledgment from Anthropic. Full transcripts, PoC evidence, and interactive research tools included.

33
/ 100
Emerging
No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 9 / 25
Community 4 / 25

How are scores calculated?

Stars

26

Forks

1

Language

HTML

License

—

Last pushed

Apr 08, 2026

Commits (30d)

0

GitHub

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ai-safety/Nicholas-Kloster/claude-4.6-jailbreak-vulnerability-disclosure-unredacted"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

BlackArch/blackarch

An ArchLinux based distribution for penetration testers and security researchers.

76

BishopFox/sliver

Adversary Emulation Framework

73

casdoor/casdoor

An open-source AI-first Identity and Access Management (IAM) /AI MCP & agent gateway and auth...

72

0xsyr0/Awesome-Cybersecurity-Handbooks

A huge chunk of my personal notes since I started playing CTFs and working as a Red Teamer.

71

openguardrails/openguardrails

Protect every action your agent takes.

70

Explore AI Safety Tools

All categories Trending AI Safety directory Insights