network-security-setup

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly whitelists and tests access to public, user-generated sources (e.g., *.npmjs.org, raw.githubusercontent.com, *.github.com, the "git clone https://github.com/user/repo" and "curl https://random-website.com" validation steps), so the sandbox/agent is expected to fetch untrusted third-party content that could carry prompt-injection instructions.