image-manipulation-image-magick
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of the
magickbinary to perform image processing tasks. It provides PowerShell and Bash code snippets that invoke this command locally to process image files as intended by the skill's primary function. - [PROMPT_INJECTION]: The skill processes untrusted image data from the local filesystem, which creates a surface for indirect prompt injection or tool-specific vulnerabilities if malicious images are processed.
- Ingestion points: Image files are retrieved from local paths specified in the shell scripts within
SKILL.md. - Boundary markers: No specific boundary markers or instructions are included to prevent the interpretation of data within processed files.
- Capability inventory: The skill executes the
magickCLI for identification and transformation tasks. - Sanitization: The provided examples use standard shell quoting for file paths to mitigate command injection risks.
Audit Metadata