openai-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly shows passing API keys as command-line flags (e.g., --api-key sk-...) and echoing env vars (echo $OPENAI_API_KEY), which would require the agent to include secret values verbatim in generated commands/output, creating an exfiltration risk.

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

• Potentially malicious external URL detected (high risk: 0.80). The README includes runtime installation instructions that fetch and execute remote code (e.g., git clone https://github.com/openai/openai-cli.git followed by ./scripts/run, and go install 'github.com/openai/openai-cli/cmd/openai@latest'), so these repository URLs can deliver code that is executed locally.