audio

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes ffmpeg and ffprobe commands via Python's subprocess.run module. These calls are implemented using list-based arguments rather than shell strings, which effectively mitigates command injection risks. Key files performing these operations include scripts/concat.py, scripts/trim.py, scripts/normalize.py, and scripts/_mediaskills_common.py.
  • [DATA_EXPOSURE]: The skill interacts with files in the workspace to perform audio processing. File path handling uses pathlib for normalization and implements a resolve_output helper in scripts/_mediaskills_common.py to ensure generated files are stored in a designated .mediaskills/generated directory within the workspace root.
  • [EXTERNAL_DOWNLOADS]: The skill documentation mentions the use of uv run for execution, but no remote packages or scripts are downloaded from untrusted sources. The scripts themselves have no external dependencies defined in their PEP 723 metadata blocks.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 02:52 AM
Security Audit — agent-trust-hub — audio