podcast-generation
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection, as it processes external text input within a high-capability environment (network-connected API access). \n
- Ingestion points: The
promptvariable in the Python code withinSKILL.mdis a direct entry point for untrusted data into the LLM context. \n - Boundary markers: No delimiters or specific instructions are provided to the model to ignore potential commands embedded within the text to be narrated. \n
- Capability inventory: The skill uses the
openailibrary to establish a WebSocket connection and transmit data to external Azure endpoints. \n - Sanitization: There is no evidence of input validation, character escaping, or content filtering performed on the user-provided prompt before it is sent to the model.
Audit Metadata