PromptCube
Home
AI Models
Prompt Sharing
Workflows
Q&A
Resources
Industry News
AI Coding
AI Jailbreak & Security
AI Tools
Search
中文
EN
Home
/
AI Jailbreak & Security
AI Jailbreak & Security
87 posts
Sort:
Latest
Hot
Most Replies
AI Jailbreak & Security — All Posts
Intern-BioBreaker: Biosecurity Risks in Frontier LLMs
MicroPanda
Intermediate
·
382
·
4
·
8
·
7/24/2026
AI Jailbreak & Security
AI Safety
LLM Security
Geometric Configurations: How Perturbed Jailbreaks Look to LLMs
Jamie5
Advanced
·
262
·
3
·
15
·
7/24/2026
AI Jailbreak & Security
AI Safety
LLM Security
Video LLMs are failing a basic logic test
SoloSmith
Expert
·
474
·
4
·
15
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
Claude Prompt Injection: When the AI steers the User
DrewCoder
Novice
·
110
·
3
·
14
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
AI Safety Leadership: A Revolving Door?
沪漂运营喵
Intermediate
·
337
·
3
·
4
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
AI Safety Leadership Shakeup: The CAISI Resignation
Riley2
Advanced
·
547
·
4
·
6
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
Kimi K3 Abliterated: A Tool for Blackbox Red Teaming
JordanSurfer
Intermediate
·
264
·
3
·
6
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
Moderation APIs vs LLM Judges: The Policy Gap
后端Ray
Novice
·
321
·
3
·
6
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
LLM Safety: Why ASR is a Bad Metric for Defenders
Pat31
Advanced
·
208
·
3
·
9
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
Preemptive Hardening for Agentic LLM Security
Max75
Advanced
·
321
·
4
·
6
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
DARWIN: Evolving LLM Jailbreak Framework
Dev26
Expert
·
433
·
3
·
4
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
OpenAI vs Hugging Face: The Accidental Breach
ZenMaster
Expert
·
640
·
3
·
2
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
Prismata: Stopping Cross-Site Prompt Injection
Jamie89
Intermediate
·
255
·
3
·
14
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
DNS Exfiltration via macOS Terminal ANSI Codes
Jules45
Expert
·
316
·
4
·
14
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
OpenClaw Defense: Handling Indirect Prompt Injection
Jamie67
Novice
·
230
·
4
·
13
·
7/23/2026
AI Jailbreak & Security
AI Safety
LLM Security
‹
1
2
3
4
5
6
›
Join our Telegram