elevenlabs-tts
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: References installation documentation and configuration hosted on the official GitHub repository for the inference-sh organization.\n- [COMMAND_EXECUTION]: Employs the
infshCLI andnpxfor application execution and skill installation, which is standard behavior for the inference.sh ecosystem.\n- [PROMPT_INJECTION]: Identifies a surface for indirect prompt injection because the skill accepts and processes arbitrary text input for speech synthesis.\n - Ingestion points: Data enters through the
textproperty in shell commands defined inSKILL.md.\n - Boundary markers: No delimiters or ignore instructions are present in the command templates.\n
- Capability inventory: Interaction with the ElevenLabs API is performed via the
infshtool.\n - Sanitization: No explicit validation or filtering of input text is provided in the skill instructions.
Audit Metadata