globalize-now-account-setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to construct and run CLI commands embedding ephemeral secrets (device_code, code_verifier) and references storing/reading an apiKey value, which requires the LLM to handle and potentially output secret values verbatim.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs the agent to run "npx @globalize-now/cli-client" (and related npx commands) at runtime, which fetches and executes remote package code from the npm registry as a required dependency, so remote code is executed during skill operation.