ln-830-code-modernization-coordinator

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 contains MANDATORY READ steps and explicitly instructs falling back to fetching files from the public GitHub raw URL (https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}), so the agent will ingest external, user-authored content that can materially influence runtime decisions and tool use.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill declares mandatory runtime reads and a fallback WebFetch to pull required reference files from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, meaning runtime will fetch external plain-text instructions that directly influence agent behavior and are required for operation.