ln-700-project-bootstrap

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly instructs the agent to fetch missing support files via WebFetch from a public GitHub raw URL (see top of SKILL.md: "fetch files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}") and declares several references/* files as "MANDATORY READ" that the agent must load and use for detection, planning, and delegation, meaning public third-party content can materially influence the agent's decisions and tool use.

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

• Potentially malicious external URL detected (high risk: 1.00). This skill will WebFetch required reference files at runtime from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched "MANDATORY READ" documents directly control detection rules and transformation instructions used by the agent.