🧰 Opus 4.7

The items that name it 10

• How Endor Labs AI SAST Learns What Matters to Your Organization | Blog | Endor Labs
  articleas classification.key entities2026-09-07
• Benchmarking Secure-and-Functional Remediation and How Snyk Agent Fix Lifts Frontier-Model Fix Rates by over 14%
  articleas classification.key entities2026-08-18
• XBOW: Engineering the Impossible
  articleas classification.key entities2026-08-13
• [tl;dr sec] #340 - Anthropic and Meta Agents be Hackin', Agentic Incident Response Notebooks, Figma's AI Code Scanning
  articleas classification.key entities2026-08-07
• AI Security Briefing
  articleas classification.key entities2026-07-18
• Benchmarking Endor Labs AI SAST: 2.6x more real vulnerabilities found than frontier models | Blog | Endor Labs
  articleas classification.key entities2026-07-06
• Snyk VulnBench JS 1.0: Can LLMs Find the Same Bugs Twice?
  writeupas classification.key entities2026-06-29
• Malicious Skills & Supply Chain Risks in Coding Agents
  articleas classification.key entities2026-05-14
• IronCurtain: Secure AI Agent Runtime
  writeupas tools2026-05-07

  Model used in Claude Code for guided manual analysis to confirm exploitability primitives for severity scoring

• XBOW: GPT-5.5 and Opus 4.7 in Offensive Security Workflows
  writeupas tools2026-05-06

  Anthropic LLM referenced as achieving the best results on XBOW's visual acuity ('computer use') benchmark

In every workspace you can read 14