ad-creative

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

• Third-party content exposure detected (high risk: 0.80). The skill's "How to use" explicitly directs the agent to open and inspect the upstream public GitHub repository (https://github.com/coreyhaines31/skills) and to install its bundle, which requires reading untrusted, user-generated third-party content that can change tooling and workflow behavior.