ln-114-frontend-docs-creator

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md explicitly says that if local shared/ files are missing it will "fetch files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}" and also has multiple "MANDATORY READ" entries (e.g., shared/references/docs_quality_contract.md) that the agent must load and act on, so it ingests public GitHub-hosted content that can materially influence document creation and validation.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly says that if shared/ is missing it will WebFetch required reference files at runtime from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched "MANDATORY READ" documents would directly control the agent's instructions.