adobe-illustrator-scripting
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for processing local files and user input within the Illustrator environment, creating a standard data ingestion surface.
- Ingestion points: User prompts in
scripts/find-replace-text.jsx, folder selection inscripts/batch-export-png.jsx, and sidecar file reading inreferences/extended-guide.md. - Boundary markers: Not used in the provided examples to distinguish data from instructions.
- Capability inventory: Extensive access to Illustrator's DOM including file creation, modification, and export (
doc.saveAs,doc.exportFile) across all scripts. - Sanitization: Not implemented for external content before use in DOM operations.
- Note: This ingestion surface is fundamental to the skill's primary purpose of automation and does not represent an elevated risk.
- [COMMAND_EXECUTION]: The documentation includes the use of
app.executeMenuCommand()inreferences/extended-guide.mdfor standard application tasks like copying and pasting, which is expected functionality within the Adobe scripting environment. - [SAFE]: No malicious patterns, unauthorized network access, or sensitive data exfiltration were detected. The skill's implementation of local file logging and alert suppression is consistent with professional automation workflows and follows established Adobe scripting best practices.
Audit Metadata