my-team-setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill asks the user for an Airtable Personal Access Token and instructs embedding that token verbatim into a CLI command (claude mcp add ... --token RECEIVED_TOKEN), which requires the LLM to handle and output the secret directly.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill executes "claude mcp add airtable ... npx -y airtable-mcp-server --token RECEIVED_TOKEN" at runtime, which fetches and runs code from the npm registry (e.g. https://registry.npmjs.org/airtable-mcp-server), so it executes remote code that the skill relies on.