elevenlabs-tts
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the elevenlabs and python-dotenv packages from PyPI. These are standard, versioned dependencies for interacting with the ElevenLabs API and managing environment configuration.
- [INDIRECT_PROMPT_INJECTION]: The skill processes text input to generate audio synthesis. This creates a surface where untrusted data could be processed, though the risk is limited to the content of the generated audio and the file write location.
- Ingestion points: Untrusted data enters the agent context via the text parameter in the generate_speech function within scripts/elevenlabs_tts.py.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt interpolation.
- Capability inventory: The skill has the capability to write files to arbitrary locations on the file system via the output_path parameter in scripts/elevenlabs_tts.py.
- Sanitization: No validation or escaping is performed on the input text before it is sent to the TTS engine or on the output path before file creation.
Audit Metadata