podcast-generation
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text through a
promptvariable which is directly interpolated into the message payload for the Azure OpenAI Realtime API. This creates a surface where malicious instructions embedded in the input text could potentially influence the audio generation or narrator behavior. - Ingestion points: The
promptvariable used in the message content withinSKILL.md. - Boundary markers: Absent; the input text is not wrapped in delimiters or accompanied by instructions to ignore embedded commands.
- Capability inventory: The skill utilizes the
openaiPython library to establish a WebSocket connection to external endpoints for audio streaming. - Sanitization: There is no evidence of input validation, escaping, or content filtering before the data is sent to the remote API.
Audit Metadata