speech-use
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill makes network requests to official Google Cloud API endpoints (texttospeech.googleapis.com and speech.googleapis.com) to process audio and text. These interactions are consistent with the skill's stated purpose and target well-known, trusted services.- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of audio files for transcription and text strings for speech generation.
- Ingestion points: audio_file parameter in transcribe_audio.py and text argument in generate_speech.py.
- Boundary markers: None present; the scripts process the raw input data directly.
- Capability inventory: The scripts have capabilities to read local files, write output files (WAV/TXT), and perform network operations to Google's infrastructure.
- Sanitization: None; the skill relies on the underlying Google APIs to handle the content. As a standard utility, this is considered a low-risk surface.- [COMMAND_EXECUTION]: The skill instructions utilize uv run to execute local Python scripts. The scripts are authored by the skill developer and perform legitimate speech processing tasks using standard libraries.
Audit Metadata