shortcuts-generator

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the 'open' command to trigger the import of generated plist files into the system's Shortcuts application.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by converting untrusted user instructions into executable workflow actions.
  • Ingestion points: User prompts defining desired shortcuts via instructions in SKILL.md.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate user input from the generated plist structure.
  • Capability inventory: File system writing (Python plistlib) and shell command execution (open); the generated shortcuts can perform high-risk actions like running shell scripts ('is.workflow.actions.runscript') and sending emails.
  • Sanitization: No input sanitization or parameter validation is performed on data used to construct the shortcut actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 02:08 AM