ai-podcast-creation

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 uses user-supplied text in the --input JSON (e.g., "prompt": "<...>") passed to models like openrouter/claude-sonnet-45 and then to TTS, meaning outsider-authored free text can directly become LLM-readable prompt content.