youdao-note

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs setting the API key via a command that embeds the secret as a CLI argument ("youdaonote config set apiKey YOUR_API_KEY"), which would require the agent to include a user-provided secret verbatim in generated commands or instructions.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly includes commands to clip arbitrary webpages (e.g., "youdaonote clip "https://..."") and describes clip-save JSON with bodyHtml and sourceUrl fields, showing the tool ingests open/public web content that the agent would read and could influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's setup instructs users to run a remote installer that is fetched and executed (curl -fsSL https://artifact.lx.netease.com/download/youdaonote-cli/install.sh | bash), which clearly executes remote code and is required for the CLI-based functionality.