claude-code-system-prompts

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs fetching and reading prompt files from a public GitHub repository (e.g., "git clone https://github.com/Piebald-AI/claude-code-system-prompts.git" and cat ./system-prompts/*.md), so untrusted third-party content is ingested and can directly influence agent prompts and tool behavior.