🧰 SusVibes

The items that name it 3

• Gemini 4 Argon on Cursor: solid security score, two unique solves, but slower and more expensive | Endor Labs
  writeupas frameworks and tools2026-10-20

  Benchmark measuring whether an agent's code is secure when a coding task touches code historically part of a security fix, with no hint about the vulnerability.

• Is AI Coding Safe? Introducing the Agent Security League | Blog | Endor Labs
  articleas frameworks and tools2026-10-12

  Benchmark and extensible, reproducible evaluation platform from Carnegie Mellon University testing whether agent-generated code is secure on realistic tasks

• Claude Code with Fable 5.1 posts 87.2% FuncPass and 37.4% SecPass — a new #1 on our board — while running as fast as Fable 5, costing a third of Opus 5, finishing every task with zero timeouts, and drawing less than half the confirmed cheating of both predecessors. | Blog | Endor Labs
  articleas classification.key entities2026-09-04

In every workspace you can read 9