open/ktg-plugin-marketplace
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions
ktg-plugin-marketplace/plugins/llm-security/knowledge
History
Kjell Tore Guttormsen 8d8d4e7002 feat(red-team): 8 new evasion-arsenal scenarios for v7.2.0 (E1/E4/E5/E7/E16/E17) 
Adds attack-simulator coverage for the new defenses landed earlier in
Batch B. All eight scenarios pass against the current hooks (72/72,
zero gaps). E15 (memory-poisoning glob) and E18 (entropy markdown-image
CDN allowlist) are scanner-only and have unit/integration coverage in
their respective scanner test files.

  unicode-evasion (pre-prompt-inject-scan):
    UNI-007  E1  PUA-A range hidden Unicode               → HIGH advisory
    UNI-008  E1  PUA-B range hidden Unicode               → HIGH advisory
    UNI-009  E16 Greek-Latin homoglyph fold               → CRITICAL block

  mcp-output (post-mcp-verify):
    MCP-005  E4  Markdown link-title injection            → markdown-link-title-injection
    MCP-006  E5  SVG <desc> injection                     → svg-element-injection
    MCP-007  E5  SVG <foreignObject> injection            → svg-element-injection
    MCP-008  E7  HTML comment-node injection (no marker)  → html-comment-injection

  session-trifecta (post-session-guard):
    TRI-004  E17 Escalation-after-input (WebFetch → Task) → escalation-after-input advisory

Payload helpers `buildPuaAPayload` / `buildPuaBPayload` shift each
character into Supplementary Private Use Area-A / -B respectively.
The Greek-fold payload uses Greek ι (U+03B9 → i) and ο (U+03BF → o)
so foldHomoglyphs reproduces the canonical "ignore previous
instructions" CRITICAL pattern.

Total: 64 → 72 scenarios.

Refs: Batch B Wave 6 / Step 14 / v7.2.0
2026-04-29 15:35:32 +02:00
..
attack-mutations.json feat: initial open marketplace with llm-security, config-audit, ultraplan-local 2026-04-06 18:47:49 +02:00
attack-scenarios.json feat(red-team): 8 new evasion-arsenal scenarios for v7.2.0 (E1/E4/E5/E7/E16/E17) 2026-04-29 15:35:32 +02:00
compliance-mapping.md feat(knowledge): add compliance-mapping document — EU AI Act, NIST AI RMF, ISO 42001 2026-04-10 12:29:14 +02:00
deepmind-agent-traps.md feat(knowledge): add MITRE ATLAS IDs to OWASP files + Norwegian regulatory context 2026-04-10 12:49:10 +02:00
ide-extension-threat-patterns.md docs(llm-security): add JetBrains sections to ide-extension-threat-patterns 2026-04-18 10:00:59 +02:00
jetbrains-marketplace-api-notes.md docs(llm-security): add knowledge/jetbrains-marketplace-api-notes.md 2026-04-18 10:02:04 +02:00
marketplace-api-notes.md feat(llm-security): /security ide-scan <url> — Marketplace/OpenVSX/direct VSIX (v6.4.0) 2026-04-17 17:16:26 +02:00
mcp-threat-patterns.md feat(knowledge): add MITRE ATLAS IDs to OWASP files + Norwegian regulatory context 2026-04-10 12:49:10 +02:00
mitigation-matrix.md docs(llm-security): A3 honesty-sweep — 7 sitater nedtonet (critical-review §9) 2026-04-29 11:52:55 +02:00
norwegian-context.md feat(knowledge): add MITRE ATLAS IDs to OWASP files + Norwegian regulatory context 2026-04-10 12:49:10 +02:00
owasp-agentic-top10.md feat(knowledge): add MITRE ATLAS IDs to OWASP files + Norwegian regulatory context 2026-04-10 12:49:10 +02:00
owasp-llm-top10.md feat(knowledge): add MITRE ATLAS IDs to OWASP files + Norwegian regulatory context 2026-04-10 12:49:10 +02:00
owasp-skills-top10.md feat(knowledge): add MITRE ATLAS IDs to OWASP files + Norwegian regulatory context 2026-04-10 12:49:10 +02:00
prompt-injection-research-2025-2026.md feat: initial open marketplace with llm-security, config-audit, ultraplan-local 2026-04-06 18:47:49 +02:00
secrets-patterns.md feat: initial open marketplace with llm-security, config-audit, ultraplan-local 2026-04-06 18:47:49 +02:00
skill-registry.json feat: initial open marketplace with llm-security, config-audit, ultraplan-local 2026-04-06 18:47:49 +02:00
skill-threat-patterns.md feat: initial open marketplace with llm-security, config-audit, ultraplan-local 2026-04-06 18:47:49 +02:00
top-jetbrains-plugins.json feat(llm-security): seed top-jetbrains-plugins.json + loadJetBrainsBlocklist export 2026-04-18 09:56:55 +02:00
top-packages.json feat: initial open marketplace with llm-security, config-audit, ultraplan-local 2026-04-06 18:47:49 +02:00
top-vscode-extensions.json feat(llm-security): add /security ide-scan — VS Code / JetBrains extension prescan (v6.3.0) 2026-04-17 16:23:35 +02:00
typosquat-allowlist.json feat(llm-security): v7.0.0 commit 4 — typosquat allowlist for short legit names 2026-04-19 22:03:46 +02:00