looker-mcp-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill contains examples and config snippets that instruct embedding API credentials and bearer tokens verbatim into curl commands, Docker/env command lines, and client config files, which requires the LLM/agent to handle and output secret values directly.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's standalone deployment instructs running a remote Docker image (us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox:latest) which will be pulled and executed at runtime, meaning the skill depends on externally fetched code that executes on the host.