agent-analytics

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 query analytics data and raw event logs via CLI commands (events, breakdown, sessions), which ingest outsider-authored user inputs like paths, referrers, and event properties submitted by visitors to the monitored website.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the execution of an externally hosted npm package via npx (@agent-analytics/cli), which constitutes an operational dependency.