tesseract-audio

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download the Tesseract CLI binary and its associated installation scripts directly from the author's GitHub repository (mirage-hq/tesseract). It also facilitates downloading audio samples from established community repositories like Freesound.org and GitHub (sgossner/VSCO-2-CE).
  • [COMMAND_EXECUTION]: Included Python scripts (tesseract_sound.py and tesseract_media.py) utilize the subprocess module to execute ffmpeg and ffprobe for audio synthesis, measurement, and waveform generation. These operations are restricted to media processing tasks defined in the skill's instructions.
  • [DYNAMIC_EXECUTION]: The skill's primary function involves authoring JavaScript snippets (layerTimeJsCode) and WGSL (WebGPU Shading Language) modules for procedural animations and custom visual shaders within the Tesseract engine. This is the documented mechanism for DAW and visual effects authoring.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as user-supplied audio files, video footage, and MIDI files. This constitutes an ingestion surface where malicious instructions could potentially be embedded in media metadata or transcripts, though the skill provides guidance for manual inspection and verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 10:57 AM