media-utils
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- COMMAND_EXECUTION (SAFE): The scripts use subprocess.run with argument lists rather than shell strings, effectively preventing shell injection. Parameters such as filenames are passed as discrete arguments and are not interpreted by a shell environment.
- PROMPT_INJECTION (SAFE): No instructions were found that attempt to override agent behavior, bypass safety filters, or extract system prompts. The skill documentation is focused on utility functionality.
- DATA_EXFILTRATION (SAFE): No unauthorized network operations (such as curl or requests) or attempts to access sensitive local files (such as SSH keys or credentials) were detected. All operations are local to the media files provided for processing.
- EXTERNAL_DOWNLOADS (LOW): The documentation recommends installing standard Python packages like markdown and weasyprint. These are reputable libraries from established registries. While weasyprint can be a vector for SSRF if used with untrusted input, the specific script using it was not included for analysis.
Audit Metadata