podcastfy-clawdbot

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

• Third-party content exposure detected (high risk: 0.90). The wrapper explicitly accepts arbitrary public URLs (see SKILL.md quick start and scripts/podcastfy_generate.py which passes --url values into podcastfy.generate_podcast and uses Playwright/website_extractor to fetch webpage content), so the agent ingests untrusted third‑party web pages whose text can be read and summarized by the LLM and therefore could carry indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The script requires at least one runtime URL (e.g., the example placeholder "https://example.com/article") which is fetched and fed into podcastfy/LLM to generate transcripts, so external web content can directly control the model's prompts/outputs.