seawolf PRO
seawolf2357
AI & ML interests
None yet
Recent Activity
reacted to SeaWolf-AI's post with š about 12 hours ago
š”ļø AI Model Hacking Hackathon is LIVE Ā· USD 4,500 in prizes
AI agents now read mail, open files, browse the web and run shell commands. A single crafted email was enough for EchoLeak (CVE-2025-32711), and a coding agent wiped a production database during a code freeze. The risk has moved from what models say to what agents do.
ViKernel is a security kernel that sits at the tool-call boundary, like an OS kernel at the system-call boundary. Every tool call gets ALLOW or DENY before it runs, and every verdict goes into a hash-chained audit trail.
Now we want you to break it. š
šÆ Season 1 Ā· Agent Hijack (Beginner)
šµļø Season 2 Ā· Data Exfiltration (Intermediate)
āļø Season 3 Ā· Hidden Instruction (Advanced): plant a mail, a document or a page and make the agent act on it
š„ Season 4 Ā· Kernel Breach (Expert)
Every season has two prizes: Top score (USD 500, and USD 1,000 in Season 4) and a USD 500 Special Award for the most outstanding finding.
Seasons 1, 2 and 3 are open now until Jan 16. Season 4 opens right after.
Day 1: 6 players, 56 submissions, 14 accepted breaches, and 11 causes fixed in the kernel the same day.
ā
Hugging Face sign-in + a browser. No coding, no GPU.
ā
Mock tools, so attack freely.
ā
Prompt guide with copy-ready attacks for every season.
ā
Live leaderboard and a measured baseline to beat.
Safe AI is built by everyone who tries to break it. Bring your strangest idea. š¤
š¹ļø Start hacking: https://huggingface.co/spaces/FINAL-Bench/ViKernel-RedTeam
š Read the full story: https://huggingface.co/blog/FINAL-Bench/ai-model-hacking-hackathon-safe-ai-is-built-by-eve
#AISafety #RedTeaming #AIAgents #PromptInjection #Hackathon liked a Space about 12 hours ago
FINAL-Bench/ViKernel-RedTeam liked a model 4 days ago
FINAL-Bench/Darwin-Prediction-Weather