ln-621-security-auditor

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs that if shared/ is missing the agent should fetch files via WebFetch from the public URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those MANDATORY READ reference files are parsed and used to drive detection, scoring, and actions—so untrusted public GitHub content can materially influence behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs at runtime to WebFetch required shared files from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, which would load external raw GitHub content that directly controls the agent's instructions and templates.