songsee

Warn

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's metadata contains installation instructions for an external binary via a third-party Homebrew tap (steipete/tap/songsee). As the source repository is hosted under a personal account rather than a verified organization, it is considered an unverified dependency that could pose a supply chain risk.
  • [COMMAND_EXECUTION]: The skill provides patterns for executing the songsee command-line utility. The agent is instructed to run this tool with various parameters to process audio files and generate spectrogram images on the local system.
  • [PROMPT_INJECTION]: The skill processes untrusted audio data, which serves as an ingestion point for indirect prompt injection. A specifically crafted audio file could attempt to exploit vulnerabilities in the songsee tool or its media decoding dependencies like ffmpeg. Ingestion points: Audio files loaded via file path or stdin. Boundary markers: None provided to separate data from instructions. Capability inventory: Execution of a third-party CLI binary. Sanitization: No validation or sanitization is performed on the audio input before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 16, 2026, 09:14 PM
Security Audit — agent-trust-hub — songsee