elevenlabs
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements standard integration with ElevenLabs for text-to-speech, sound effects, and music generation without any detected security vulnerabilities.
- [CREDENTIALS_SAFE]: The skill correctly handles authentication by using environment variables (ELEVENLABS_API_KEY) and provides clear instructions to avoid hardcoding or leaking credentials in shared environments.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external text prompts to generate audio files, presenting an indirect injection surface. Evidence: 1. Ingestion points: text and prompt parameters in SKILL.md. 2. Boundary markers: None. 3. Capability inventory: Writes audio files and manifest.json to local storage. 4. Sanitization: Not implemented in provided snippets. The risk is considered safe due to the restricted nature of audio synthesis.
- [COMMAND_EXECUTION]: Example commands for generating voiceover assets use local scripts (tools/voiceover.py) that are part of the intended developer workflow and do not involve untrusted network input.
Audit Metadata