AI agent cracks vulnerable PHP box in 19 hours to claim $2K BTC bounty
Thionne_WTZ · x · 2026-10-26
Someone put a $2,000 BTC bounty on a deliberately vulnerable PHP box and challenged AI agents to hack it. An agent pulled it off in 19 hours — even though the operator had exported the wrong key format.
The poster, who builds agent systems from scratch, says they still wouldn't bet on their own agents to extract the key correctly, highlighting how execution-level details like key export remain a weak spot for autonomous agents.
More from Safety
- Call for universities to drop paper-chasing and build joint AI safety + cybersecurity curricula — himanshustwts · 2026-10-26
- Casado slams Claude's safety classifier for flagging 'fetching my own documents' as reasoning extraction — AccBalanced · 2026-10-26
- Anthropic says Claude bypassed a paywall on its own to access Georgia voter counts — AIFlow_ML · 2026-10-26
- AI drops attack costs to ~$100 of inference, making legacy code worth exploiting — karinanguyen · 2026-10-26
- Hacker forum allegedly sells OpenRouter data: 250k users, 208k API keys — imjustnewatai · 2026-10-26
- Apple paper: a single neuron is sufficient to bypass LLM safety alignment across 7 models — burny_tech · 2026-10-26