auto-deskew
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to invoke
magick(ImageMagick),python(viauv run), andawk. These are the primary mechanisms for its stated functionality of image processing. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of image files and filenames.
- Ingestion points: Image files provided as input via the
$INvariable. - Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore embedded content within the processed files.
- Capability inventory: The skill utilizes subprocess execution for image manipulation (
magick), mathematical calculations (awk), and line detection (python+opencv-python-headless). - Sanitization: The skill uses shell quoting for primary file path variables (e.g.,
"$IN","$OUT"), which is a best practice for preventing command injection, though some internal variables like${THRESHOLD}are shown unquoted in the procedure templates.
Audit Metadata