ln-200-scope-decomposer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly falls back to fetching required runtime/reference files from the public URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path} and mandates reading shared/references/*.md, so it will ingest and act on untrusted public GitHub content that can influence coordinator decisions and tool invocations.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires MANDATORY READ of shared reference files and instructs that if missing they be fetched at runtime via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, so external content would be loaded during execution and directly control the agent's runtime contracts/instructions.