elevenlabs-dialogue
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides links to installation documentation and scripts hosted on the vendor's GitHub repository (inference-sh). These are handled as informational references to vendor-provided tools.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied dialogue text for audio generation, identifying a potential injection surface. 1. Ingestion points: The
--inputJSON object in SKILL.md examples. 2. Boundary markers: Absent. 3. Capability inventory: Network access to the ElevenLabs API via the vendor's CLI tool. 4. Sanitization: Absent.
Audit Metadata