Kjell Tore Guttormsen 8a772b0534 docs(llm-security): SkillSpector gap analysis + reviewed execution plan ... Brief + 8-step trekplan for 3 new dep-free scanners: TRG (trigger-abuse), SIG (signature engine over the decode pipeline), AST (Python AST taint). Adversarial review fixed 3 blockers + 7 majors on draft 1 (59/D -> 86/B). STATE.md prepped as a self-contained cold-start for /trekexecute next session. Un-gitignore STATE.md (global ~/.claude rule overrides old polyrepo convention); ignore generated plan annotation HTML. No scanner code yet. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01V3s6WnubSSrFjAQTLQdVbG		2026-06-20 09:00:24 +02:00
..
plans	docs(llm-security): SkillSpector gap analysis + reviewed execution plan	2026-06-20 09:00:24 +02:00
ci-cd-guide.md	feat(ci): add CI/CD integration — --fail-on, --compact, pipeline templates	2026-04-10 14:59:05 +02:00
critical-review-2026-04-20.md	docs(llm-security): add critical review 2026-04-20 (v7.0.0 adversarial audit)	2026-04-19 23:27:52 +02:00
defense-philosophy.md	chore: WIP marketplace doc adjustments across plugins	2026-05-18 12:04:02 +02:00
scanner-reference.md	chore(llm-security): v7.7.2 — language consistency pass	2026-05-19 06:47:44 +02:00
security-hardening-guide.md	docs(hardening-guide): 8.6 — sandbox-architecture rationale (no code consolidation)	2026-04-30 16:55:45 +02:00
version-history.md	chore(llm-security): v7.7.2 — language consistency pass	2026-05-19 06:47:44 +02:00