youdaonote

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to prompt for the user's API key and then run commands like youdaonote config set apiKey <用户提供的Key> (and includes config set apiKey YOUR_KEY), which requires embedding the secret verbatim into generated command output — an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill's required CLI workflow includes a webpage clipping command that fetches arbitrary public URLs (e.g., youdaonote clip "https://example.com/article" in SKILL.md) and the agent is explicitly expected to inspect the fetched content (e.g., markdown-detection rules that change save behavior), so untrusted third‑party page content can influence decisions and actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to run a remote installer at runtime using "curl -fsSL https://artifact.lx.netease.com/download/youdaonote-cli/install.sh | bash", which fetches and executes remote code as a required dependency.