temporal-cloud-setup

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

• Third-party content exposure detected (low risk: 0.10). The workflow invokes scripts/provision.sh which clones public GitHub repositories (repo_url_for_sdk), exposing the agent to any outsider-authored code or free text present in those repositories.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 0.70). The skill sets up Temporal Cloud, creates Cloud namespaces and API keys, and runs workflows via a provisioning script. The creation of a Cloud namespace is explicitly documented as a billable cloud operation that creates real resources in a Temporal Cloud account (SKILL.md:497-498: "> ⚠️ Heads-up: this creates real resources in your Temporal Cloud account — a namespace and an API key — which may incur cost."). This constitutes an in-scope direct financial operation (charges/purchases/cloud resource creation). There is no qualifying independent access control enforced by the service or execution layer for this direct operation (approval relies solely on the user's local tool-permission prompt or manual go-ahead steps, rather than independent service-layer authentication gating the payment/charge route itself). Therefore, the direct financial operation without established qualifying control falls under High severity.