podcast-generation

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill utilizes environment variables for Azure OpenAI credentials (AZURE_OPENAI_AUDIO_API_KEY) and endpoints. No hardcoded secrets or sensitive data exfiltration to untrusted domains were found.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided text prompts for narration, representing a potential surface for indirect prompt injection.
  • Ingestion points: User-provided prompt variable used in the WebSocket message content in SKILL.md.
  • Boundary markers: None are present in the provided code snippets to delimit user content from system instructions.
  • Capability inventory: Network operations via WebSocket to Azure OpenAI endpoints.
  • Sanitization: No explicit sanitization or filtering of the input text is shown.
  • [SAFE]: The code follows standard integration patterns for the OpenAI Python library and well-known cloud services. No obfuscation, persistence mechanisms, or unauthorized privilege escalations were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 06:59 AM