image-manipulation-image-magick

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands through the ImageMagick suite (magick and identify) to perform file-system operations on images.
  • [EXTERNAL_DOWNLOADS]: Provides references to installing system-level dependencies from official and well-known package managers such as apt for Debian/Ubuntu and Homebrew for macOS.
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface as the skill processes external image files which could potentially contain malicious payloads targeting vulnerabilities in image processing libraries.
  • Ingestion points: Files located at paths like path/to/images/* as seen in SKILL.md.
  • Boundary markers: None provided; the skill does not implement delimiters or 'ignore' instructions for the data being processed.
  • Capability inventory: Shell command execution via subprocess calls to the magick utility (SKILL.md).
  • Sanitization: No validation or sanitization of input image files is specified before they are passed to the command-line tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 04:43 PM