ln-112-project-core-creator

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to WebFetch shared files from the public URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path} (and marks several files as "MANDATORY READ"), so the agent will ingest and act on public GitHub content that could contain untrusted, user-generated instructions influencing document generation and validation.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs at runtime to WebFetch templates and reference files if shared/ is missing from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, which would load remote document content that directly controls the agent's document-generation behavior and is treated as a required dependency.