Write-time defensive layer for Python pipelines that persist LLM output: sanitize, fence, tool-less quarantined transform, capability isolation, scan before persist, fail-secure.
Updated 2026-09-08 04:10:55 +00:00
Security scanning, auditing, and threat modeling for Claude Code projects. OWASP LLM Top 10 (2025) and Agentic AI Top 10.
Updated 2026-08-21 09:30:20 +00:00
Runtime-neutral core for LLM and agent security detection: detector data, normative contracts and a conformance corpus that several runtimes can share.
Updated 2026-08-21 09:23:03 +00:00