cio

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly tells the agent to fetch a public README via "curl -fsSL https://raw.githubusercontent.com/customerio/cio-cli/main/README.md", which is user-controlled public GitHub content the agent is expected to read and use to determine/install commands, so it can materially influence behavior and enable indirect prompt injection.