podcastfy-generator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and fetches arbitrary public URLs and YouTube videos (see SKILL.md/README and scripts/generate.py which passes URLs into the VENV_CODE calling podcastfy.generate_podcast), and feeds that untrusted, third‑party content into the Gemini LLM to generate dialogue and drive TTS/output, so webpage/transcript content can materially influence generation and downstream actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches arbitrary, user-supplied URLs at runtime (e.g., https://example.com/article) and passes the fetched content into the podcastfy LLM pipeline (generate_podcast), which injects that external content into the model context and thus can directly control prompts/output.