openverse-sfx
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches audio files from the Openverse API (api.openverse.org) and other external URLs provided via the search script. These downloads are handled by
scripts/sfx_fetch.pyand are stored locally for media processing. - [COMMAND_EXECUTION]: The skill relies on shell command execution via Python's
subprocess.runto invoke FFmpeg for audio normalization, mixing, and verification tasks. These operations are necessary for the skill's core functionality. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data in the form of audio files, video files, and metadata (attribution text) from the Openverse API. While this creates a theoretical attack surface, the skill processes this data using signal analysis (librosa) and command-line media filters (FFmpeg) rather than interpreting it as instructions, which significantly limits the risk.
Audit Metadata