Post
2,022
π‘οΈ AI Model Hacking Hackathon is LIVE Β· 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. π
π― Season 1 Β· Agent Hijack (Beginner)
π΅οΈ Season 2 Β· Data Exfiltration (Intermediate)
βοΈ Season 3 Β· Hidden Instruction (Advanced): plant a mail, a document or a page and make the agent act on it
π₯ Season 4 Β· 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.
β Hugging Face sign-in + a browser. No coding, no GPU.
β Mock tools, so attack freely.
β Prompt guide with copy-ready attacks for every season.
β Live leaderboard and a measured baseline to beat.
Safe AI is built by everyone who tries to break it. Bring your strangest idea. π€
πΉοΈ Start hacking: FINAL-Bench/ViKernel-RedTeam
π 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
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. π
π― Season 1 Β· Agent Hijack (Beginner)
π΅οΈ Season 2 Β· Data Exfiltration (Intermediate)
βοΈ Season 3 Β· Hidden Instruction (Advanced): plant a mail, a document or a page and make the agent act on it
π₯ Season 4 Β· 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.
β Hugging Face sign-in + a browser. No coding, no GPU.
β Mock tools, so attack freely.
β Prompt guide with copy-ready attacks for every season.
β Live leaderboard and a measured baseline to beat.
Safe AI is built by everyone who tries to break it. Bring your strangest idea. π€
πΉοΈ Start hacking: FINAL-Bench/ViKernel-RedTeam
π 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