ln-722-backend-generator

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs the skill to fetch missing shared/ files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, so the agent will ingest public GitHub content (third‑party/untrusted) that directly informs generation rules and can materially influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill will, at runtime, fetch shared generation files from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those remote files are used as generation templates/rules that directly influence the agent's prompts/instructions if local copies are missing.