text-to-speech
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external text data through a high-capability toolset.
- Ingestion points: Untrusted data enters the context through the
textparameter in thetextToSpeechandgenerateSpeechfunctions defined in SKILL.md. - Boundary markers: There are no delimited boundaries or specific instructions provided to the agent to treat the input text as data rather than instructions.
- Capability inventory: The skill possesses network capabilities, making HTTP POST requests to the HeyGen API (
api.heygen.com) using thefetchandrequestslibraries. - Sanitization: The provided code snippets do not perform any escaping, validation, or filtering of the input text before it is transmitted to the remote API service.
Audit Metadata