setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to extract or generate an auth token/project ID and embed the auth token verbatim into CLI commands (e.g., --auth-token {TOKEN}), which requires the LLM to handle and output secrets directly.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs running "npx @subframe/cli@latest init ..." which fetches and executes the remote @subframe/cli package at runtime (https://www.npmjs.com/package/@subframe/cli), and this CLI is required for setup, so it is a runtime external dependency that executes remote code.