ElevenLabs CLI
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill content.
- [CREDENTIALS_UNSAFE]: The skill follows security best practices by recommending the use of the
ELEVENLABS_API_KEYenvironment variable for authentication instead of hardcoding API keys. - [INDIRECT_PROMPT_INJECTION]: The skill uses commands that ingest external text for audio generation, which constitutes a potential injection surface.
- Ingestion points: Text input provided to the
elevenlabs tts --textcommand. - Boundary markers: None identified in the provided command examples.
- Capability inventory: Execution of the
elevenlabsCLI tool for speech generation and voice management. - Sanitization: Not specified in the skill instructions.
Audit Metadata