ln-400-story-executor

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

• Third-party content exposure detected (high risk: 0.80). The skill's required runtime steps include "MANDATORY READ" of files in shared/references and an explicit fallback that, if shared/ is missing, fetches those files via WebFetch from the public URL https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, so the agent will fetch and read public, user-authored GitHub content that can alter orchestration behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly states that if local shared/ files are missing it will WebFetch them at runtime from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched files include agent prompt templates and executable scripts (shared/agents/prompt_templates/.md and shared/scripts/.mjs) which directly shape prompts and are executed by node, making this a required runtime dependency that controls agent behavior and code execution.