Scroll trīgintā trēs
Arcane curation from the IndieWeb, Fediverse and Cybersecurity realms
SCAM — How safe is your AI agent?
1password.github.ioAn open-source benchmark by 1Password that tests whether AI agents can handle real security threats during everyday tasks. View the leaderboard, watch replays, and try the security skill.
GitHub - 1Password/SCAM: SCAM - Security Comprehension Awareness Measure | Open-source benchmark that tests AI agents' security awareness during realistic, multi-turn workplace tasks.
SCAM - Security Comprehension Awareness Measure | Open-source benchmark that tests AI agents' security awareness during realistic, multi-turn workplace tasks. - 1Password/SCAM
1Password's new benchmark teaches AI agents how not to get scammed | 1Password
AI agents are remarkably poor at avoiding threats. The SCAM benchmark puts AI agents in realistic scenarios, confronts them with common security threats, and uses a novel framework to help them improve.
[tl;dr sec] #316 - How Trail of Bits uses Claude Code, GitHub Threat Intel, Open Source AI Pentesting Tools
Extensive guide on being a Claude Code power user, tracking threat actors on GitHub, open source AI-powered pentesting tools