cyrus-setup-github

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly asks the user to paste the redirect URL containing the one-time code and then directs constructing/issuing commands (e.g., gh api /app-manifests//conversions) that embed that code, meaning the LLM would need to receive and output a secret-like value verbatim despite other guidance to handle secrets via Bash only.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Part B (GitHub App + Webhooks) explicitly configures webhooks to receive PR comments and review events from GitHub (user-generated, public/untrusted content) which the agent is expected to read and act on (respond to @mentions and take actions), so third-party content can materially influence its behavior.