skill

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow instructs the agent to run and parse results from the public Sundial Hub (e.g., "npx sundial-hub find 'QUERY' --json" and related https://sundialhub.com URLs), which returns user-contributed skill listings that the agent must read and act on (install/publish decisions), exposing it to untrusted third-party content that could embed malicious instructions.