servicenow

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

• Third-party content exposure detected (medium risk: 0.30). The skill instructs the agent to read ServiceNow incidents and tickets, which can contain outsider-authored free text from users or external reporters.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation of a third-party CLI package via npm from an arbitrary repository source, which constitutes an unverifiable runtime external dependency.