photocraft-batch-image-delivery
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/contact_sheet.pyusessubprocess.runto execute a command-line interface tool (provided via the--cliargument). The script executes commands withshell=False(default) using a list of arguments, which is a secure practice to prevent shell injection. - Evidence:
process = subprocess.run([str(cli), *args], capture_output=True, text=True, encoding='utf-8', errors='replace')inscripts/contact_sheet.py. - [INDIRECT_PROMPT_INJECTION]: The skill processes external image files and uses their filenames as text labels in the generated contact sheets. This represents a data ingestion surface where external content is interpolated into tool commands.
- Evidence: The script reads image file metadata and incorporates the filename into the
type.createcommand parameters. It includes validation to ensure filenames do not contain control characters or newlines. - [EXTERNAL_DOWNLOADS]: The documentation mentions installing a companion skill
photocraft-editorusingnpx. This reference is to a resource within the same vendor's ('full-aigc-skills') infrastructure. - Evidence:
npx skills add full-aigc-skills/photocraft-skills --skill photocraft-editorinSKILL.md.
Audit Metadata