podcast-generation
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill correctly instructs users to manage sensitive credentials like API keys through environment variables, avoiding hardcoded secrets.
- [SAFE]: Network activity is restricted to official Azure OpenAI endpoints for the purpose of audio generation.
- [PROMPT_INJECTION]: The skill processes user-supplied text for narration via the OpenAI Realtime API. This creates an indirect prompt injection surface where the source text could attempt to influence the narration style or content. However, because the skill's capabilities are restricted to generating audio and transcripts, there is no risk of system-level compromise.
- Ingestion points: The 'prompt' variable in the Python snippet.
- Boundary markers: None used in the API request.
- Capability inventory: Limited to audio generation and transcript collection via WebSocket.
- Sanitization: None observed.
Audit Metadata