azure-text-to-speech
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection by processing external text input for audio synthesis.
- Ingestion points: The
textparameter in thetts.executemethod defined inSKILL.mdserves as the entry point for untrusted data. - Boundary markers: The documentation specifies that text is XML-escaped automatically by the tool, which helps mitigate SSML injection.
- Capability inventory: The skill performs network operations to Microsoft Azure endpoints and writes audio data to the local file system (e.g.,
output_path). - Sanitization: Input text undergoes automatic XML escaping as a security best practice described in the limits and tips section.
Audit Metadata