ai-dev-tools

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs downloading and executing remote shell scripts from third-party vendor domains (claude.ai, chatgpt.com, x.ai, code.kimi.com, pi.dev, gh.io) at runtime, with strong/official provenance for major vendors but unverified/third-party origins for others like pi.dev, making operational dependencies present.