resolve-media-pool
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external media files and card inventories. This presents an attack surface where malicious instructions could be embedded in file metadata. However, the skill includes safety boundaries, such as excluding non-media files and protecting camera originals, which mitigates this risk.
- [COMMAND_EXECUTION]: The skill references the use of ffmpeg and ffprobe for offline media verification and inventory tasks. These are established utilities required for the skill's media processing functionality.
- [SAFE]: No other malicious patterns, such as data exfiltration, obfuscation, or persistence mechanisms, were identified in the skill instructions or tool definitions.
Audit Metadata