image-manipulation-image-magick
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates image processing by providing templates that execute the
magick(ImageMagick) binary through shell (Bash) and PowerShell commands as documented inSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data which presents a potential injection surface.
- Ingestion points: Local filesystem paths and image metadata are ingested through commands like
Get-ChildItemandmagick identifyinSKILL.md. - Boundary markers: No specific delimiters are used in the command templates.
- Capability inventory: The skill executes system commands via the
magickexecutable and performs file system traversal. - Sanitization: The skill includes proactive security guidance in the 'Guidelines' section of
SKILL.md, specifically advising the agent to 'Always quote file paths' to mitigate shell-based command injection.
Audit Metadata