new-relic

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

• Third-party content exposure detected (low risk: 0.10). The workflow interacts with New Relic via API/CLI actions and proxy requests, which may retrieve data (such as alert incidents or application metrics) that could contain outsider-submitted content, representing an active fetch/search exposure of external observability data.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the installation and execution of npm packages from @membranehq (@membranehq/cli), which is a common/reputable unofficial publisher (or third-party enterprise service not possessing strong first-party verification for arbitrary agent execution contexts), representing a medium dependency tier.