youtube-shorts-generator

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

• Third-party content exposure detected (high risk: 0.85). The required runtime path “Rank highlights” uses an LLM to scan the MuAPI /openai-whisper verbose_json transcript segments (timestamped text) produced from the user-supplied YouTube URL/mp4, which is outsider-authored free text not authored by the operating user.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs cloning and running code from https://github.com/SamurAIGPT/AI-Youtube-Shorts-Generator.git, so external code would be fetched and executed and can contain the prompt/configuration that directly controls the agent’s behavior.