integration

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill scans and reads installed marketplace plugin files from ~/.claude/marketplaces/cadrianmae-claude-marketplace/plugins/ (plugin.json, skills//SKILL.md, commands/.md) — third-party plugin content that is untrusted and is imported into CLAUDE.md, so it can be interpreted and materially influence agent behavior.