gitnexus-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes a --api-key command-line flag (and examples imply passing an LLM API key on the command line), which encourages embedding API keys verbatim in commands/outputs and thus risks secret exfiltration.

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

• Potentially malicious external URL detected (high risk: 0.70). The README instructs regenerating the runner with commands like "npx gitnexus analyze" (which fetches and executes the gitnexus package from the npm registry, e.g. https://registry.npmjs.org/gitnexus), and that fetched code generates CLAUDE.md/AGENTS.md context files used to control agent prompts, so remote code fetched at runtime can directly control agent instructions.