ktg-plugin-marketplace/plugins/llm-security/tests
Kjell Tore Guttormsen 716c8384d9 feat(post-mcp-verify): E5 — scan SVG desc/title/metadata/foreignObject
SVG containers carry text that is invisible in the rendered image but
fully parsed by an agent reading the source. <desc>, <title>,
<metadata>, and <foreignObject> are all valid surfaces for adversarial
injection.

Adds a per-element extractor inside the existing HTML-tag gate, gated
on /<svg[\s>]/i so it only fires for actual SVG content. Inner text is
HTML-entity-decoded then run through scanForInjection. Emits at the
strongest tier with category svg-element-injection.

+3 tests (62 → 65).

Refs: Batch B Wave 4 / Step 10 / v7.2.0
2026-04-29 14:54:58 +02:00
..
fixtures fix(memory-poisoning): E15 — add .claude/agents/*.md to target glob 2026-04-29 14:13:01 +02:00
helpers test(llm-security): add JetBrains fixture tree + build helper 2026-04-18 10:49:49 +02:00
hooks feat(post-mcp-verify): E5 — scan SVG desc/title/metadata/foreignObject 2026-04-29 14:54:58 +02:00
lib feat(injection): E16 — homoglyph NFKC fold before every pattern match 2026-04-29 14:22:05 +02:00
scanners fix(memory-poisoning): E15 — add .claude/agents/*.md to target glob 2026-04-29 14:13:01 +02:00