elevenlabs-performance-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides functions for processing text input to generate audio, which presents a surface for indirect instructions if the source text is untrusted.
- Ingestion points: Multiple functions in
references/implementation.mdaccept string arguments for conversion to speech. - Boundary markers: There are no specific delimiters or instructions implemented to distinguish between text data and potential control sequences.
- Capability inventory: The skill utilizes network connectivity to interact with the ElevenLabs API and possesses
Writepermissions for file system operations. - Sanitization: The code snippets do not include logic for sanitizing or validating the input text before transmission to the remote TTS service.
Audit Metadata