mcp-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes examples that embed credentials/tokens directly into commands (e.g., --auth-user "username:password" and --auth-header "Bearer your-token-here"), which would require the LLM to handle or output secret values verbatim.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). The instructions tell the user to clone and build a binary from a GitHub repo owned by a minimal/unknown account ("https://github.com/f/mcptools.git"), which is a higher-risk source for executables; the other URLs are localhost or example placeholders and are not themselves distribution risks.

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

• Potentially malicious external URL detected (high risk: 0.90). The SKILL.md explicitly instructs cloning and building remote code with "git clone --depth 1 https://github.com/f/mcptools.git" (followed by a local build), which fetches and executes remote code during setup/runtime.