auto-white-balance
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs shell command execution using ImageMagick (magick or convert), awk, and xargs to process images and handle batch operations.
- [DYNAMIC_EXECUTION]: The skill utilizes shell command substitution $(...) and ImageMagick's internal fx expression engine to dynamically calculate and inject values for color correction gains and luminance adjustments into the final command lines.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted image data, which presents a vulnerability surface for attacks targeting the image parser or metadata processing.
- Ingestion points: External image files (JPEG, PNG, TIFF, WebP) and directories referenced in SKILL.md.
- Boundary markers: Absent for external file processing.
- Capability inventory: Subprocess execution and file writing across all defined procedures in SKILL.md.
- Sanitization: Shell variables for paths are double-quoted in scripts to prevent simple argument injection.
Audit Metadata