pulumi-overview

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to capture and surface the Pulumi account claim URL (and related agent access token/banner) verbatim, which are secret credentials that must not be exfiltrated inadvertently.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs using "npx pulumi ..." which will fetch and execute the Pulumi CLI package from the npm registry at runtime (e.g. https://registry.npmjs.org), so remote code is downloaded and executed as part of normal operation.