claude-plugin-validation

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

• Third-party content exposure detected (high risk: 0.90). This skill reads and parses arbitrary plugin files from third-party plugins (e.g., .claude-plugin/plugin.json, agents/.md, skills//SKILL.md and other files via os.walk), so the agent ingests untrusted, user-provided content as part of its validation workflow.