elevenlabs-tts
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or behaviors were identified. The skill's functionality is consistent with its description as a text-to-speech interface.
- [EXTERNAL_DOWNLOADS]: The skill references installation instructions and related tools from the
inference-shorganization on GitHub. These references are standard for the skill's infrastructure and do not represent a security risk. - [INDIRECT_PROMPT_INJECTION]: The skill consumes text input via the
beltCLI to generate audio. This creates an attack surface where untrusted data could contain instructions, which is a common characteristic of text-processing skills.
Audit Metadata