suno-create

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow can ingest outsider-authored free text by searching DuckDuckGo results for lyrics (from third-party sites) and then extracting the lyrics text via browser from those pages before filling Suno’s form.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's runtime workflow explicitly navigates to and fetches lyrics pages (e.g., https://html.duckduckgo.com/html/?q={song_name}+歌词+{artist}) and then injects that fetched text into the Suno form as the generation prompt, so external web content directly controls the prompt used for generation.