buda-youtube-to-script

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests outsider-authored free text when it downloads a user-supplied public URL’s audio/transcript content (e.g., YouTube creator speech) and passes the resulting transcript text into the agent’s LLM context for rewriting (Whisper → transcript.txt → script generation).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill downloads and transcribes arbitrary user-supplied video URLs at runtime (e.g., https://www.youtube.com/watch?v=...), and the resulting transcript is fed into the model as source material that directly controls the generated talking-script prompts/content.