podcast-generation

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection.
  • Ingestion points: The 'prompt' variable is interpolated directly into the model request content within the Python snippet in SKILL.md.
  • Boundary markers: There are no protective delimiters (such as triple quotes or XML tags) or system instructions provided to the model to ignore potential commands embedded within the user-provided text.
  • Capability inventory: The skill utilizes network capabilities to communicate with Azure OpenAI via WebSockets and processes streaming audio/transcript data.
  • Sanitization: No sanitization, escaping, or validation logic is present to filter malicious instructions from the input text before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 01:31 PM