install

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly requires extracting an auth token and project ID (from user input or MCP tools) and embedding them verbatim into generated CLI commands (e.g., npx ... --auth-token {TOKEN} -p {PROJECT_ID}), which forces the LLM to handle and output secret values.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs running the npx command "npx @subframe/cli@latest init ..." which fetches and executes remote code from the npm registry at runtime and is required for installation, so it is a runtime external dependency that executes remote code.