ln-624-code-quality-auditor

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the worker to WebFetch missing shared/reference files from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path} and marks several of those fetched files as "MANDATORY READ" (detection rules, scoring and behavior), so arbitrary public GitHub-hosted content would be read and could materially change analysis logic and next actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs that if local shared/ files are missing it will fetch required "MANDATORY READ" reference docs at runtime from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched documents directly drive the worker's instructions/behavior, so this remote content controls prompts and is a required runtime dependency.