ln-720-structure-migrator

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to fetch files via WebFetch from the public GitHub URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/{path}, meaning the agent will ingest and act on public, user-controlled content that can influence its decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs a runtime WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/{path} (used when shared/ is missing) to load required reference and the "MANDATORY READ" meta_analysis_protocol.md, so external content fetched at runtime can directly control agent prompts/output and is a required dependency.