Summary
Cycode said its Agentic Code Scanning combines rule-based and agentic analysis, while its benchmark testing found two authorisation CVEs that rule engines could not express. Its new Attack Chaining capability links related findings into multi-step exploit paths.
Why it matters
The approach points application security towards reasoning about exploitability and attack paths, although the performance claims remain vendor-reported.
Related coverage
- GitHub makes the billing organisation the authority for Copilot model access
- Codex CLI 0.152 adds MCP output caps and longer shell-command deadlines
- Claude Code 2.1.252 fixes remote-session stalls and oversized failure output